Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David Miller:
 "Noteworthy changes this time around:

   1) Multicast rejoin support for team driver, from Jiri Pirko.

   2) Centralize and simplify TCP RTT measurement handling in order to
      reduce the impact of bad RTO seeding from SYN/ACKs.  Also, when
      both timestamps and local RTT measurements are available prefer
      the later because there are broken middleware devices which
      scramble the timestamp.

      From Yuchung Cheng.

   3) Add TCP_NOTSENT_LOWAT socket option to limit the amount of kernel
      memory consumed to queue up unsend user data.  From Eric Dumazet.

   4) Add a "physical port ID" abstraction for network devices, from
      Jiri Pirko.

   5) Add a "suppress" operation to influence fib_rules lookups, from
      Stefan Tomanek.

   6) Add a networking development FAQ, from Paul Gortmaker.

   7) Extend the information provided by tcp_probe and add ipv6 support,
      from Daniel Borkmann.

   8) Use RCU locking more extensively in openvswitch data paths, from
      Pravin B Shelar.

   9) Add SCTP support to openvswitch, from Joe Stringer.

  10) Add EF10 chip support to SFC driver, from Ben Hutchings.

  11) Add new SYNPROXY netfilter target, from Patrick McHardy.

  12) Compute a rate approximation for sending in TCP sockets, and use
      this to more intelligently coalesce TSO frames.  Furthermore, add
      a new packet scheduler which takes advantage of this estimate when
      available.  From Eric Dumazet.

  13) Allow AF_PACKET fanouts with random selection, from Daniel
      Borkmann.

  14) Add ipv6 support to vxlan driver, from Cong Wang"

Resolved conflicts as per discussion.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1218 commits)
  openvswitch: Fix alignment of struct sw_flow_key.
  netfilter: Fix build errors with xt_socket.c
  tcp: Add missing braces to do_tcp_setsockopt
  caif: Add missing braces to multiline if in cfctrl_linkup_request
  bnx2x: Add missing braces in bnx2x:bnx2x_link_initialize
  vxlan: Fix kernel panic on device delete.
  net: mvneta: implement ->ndo_do_ioctl() to support PHY ioctls
  net: mvneta: properly disable HW PHY polling and ensure adjust_link() works
  icplus: Use netif_running to determine device state
  ethernet/arc/arc_emac: Fix huge delays in large file copies
  tuntap: orphan frags before trying to set tx timestamp
  tuntap: purge socket error queue on detach
  qlcnic: use standard NAPI weights
  ipv6:introduce function to find route for redirect
  bnx2x: VF RSS support - VF side
  bnx2x: VF RSS support - PF side
  vxlan: Notify drivers for listening UDP port changes
  net: usbnet: update addr_assign_type if appropriate
  driver/net: enic: update enic maintainers and driver
  driver/net: enic: Exposing symbols for Cisco's low latency driver
  ...

Documentation/DocBook/80211.tmpl

@@ -325,6 +325,7 @@
           <title>functions/definitions</title>
 !Finclude/net/mac80211.h ieee80211_rx_status
 !Finclude/net/mac80211.h mac80211_rx_flags
+!Finclude/net/mac80211.h mac80211_tx_info_flags
 !Finclude/net/mac80211.h mac80211_tx_control_flags
 !Finclude/net/mac80211.h mac80211_rate_control_flags
 !Finclude/net/mac80211.h ieee80211_tx_rate

Documentation/devicetree/bindings/net/micrel-ksz9021.txt

@@ -0,0 +1,49 @@
+Micrel KSZ9021 Gigabit Ethernet PHY
+
+Some boards require special tuning values, particularly when it comes to
+clock delays.  You can specify clock delay values by adding
+micrel-specific properties to an Ethernet OF device node.
+
+All skew control options are specified in picoseconds.  The minimum
+value is 0, and the maximum value is 3000.
+
+Optional properties:
+ - rxc-skew-ps : Skew control of RXC pad
+ - rxdv-skew-ps : Skew control of RX CTL pad
+ - txc-skew-ps : Skew control of TXC pad
+ - txen-skew-ps : Skew control of TX_CTL pad
+ - rxd0-skew-ps : Skew control of RX data 0 pad
+ - rxd1-skew-ps : Skew control of RX data 1 pad
+ - rxd2-skew-ps : Skew control of RX data 2 pad
+ - rxd3-skew-ps : Skew control of RX data 3 pad
+ - txd0-skew-ps : Skew control of TX data 0 pad
+ - txd1-skew-ps : Skew control of TX data 1 pad
+ - txd2-skew-ps : Skew control of TX data 2 pad
+ - txd3-skew-ps : Skew control of TX data 3 pad
+
+Examples:
+
+	/* Attach to an Ethernet device with autodetected PHY */
+	&enet {
+		rxc-skew-ps = <3000>;
+		rxdv-skew-ps = <0>;
+		txc-skew-ps = <3000>;
+		txen-skew-ps = <0>;
+		status = "okay";
+	};
+
+	/* Attach to an explicitly-specified PHY */
+	mdio {
+		phy0: ethernet-phy@0 {
+			rxc-skew-ps = <3000>;
+			rxdv-skew-ps = <0>;
+			txc-skew-ps = <3000>;
+			txen-skew-ps = <0>;
+			reg = <0>;
+		};
+	};
+	ethernet@70000 {
+		status = "okay";
+		phy = <&phy0>;
+		phy-mode = "rgmii-id";
+	};

Documentation/devicetree/bindings/net/moxa,moxart-mac.txt

@@ -0,0 +1,21 @@
+MOXA ART Ethernet Controller
+
+Required properties:
+
+- compatible : Must be "moxa,moxart-mac"
+- reg : Should contain register location and length
+- interrupts : Should contain the mac interrupt number
+
+Example:
+
+	mac0: mac@90900000 {
+		compatible = "moxa,moxart-mac";
+		reg =	<0x90900000 0x100>;
+		interrupts = <25 0>;
+	};
+
+	mac1: mac@92000000 {
+		compatible = "moxa,moxart-mac";
+		reg =	<0x92000000 0x100>;
+		interrupts = <27 0>;
+	};

Documentation/devicetree/bindings/net/stmmac.txt

@@ -22,6 +22,11 @@ Required properties:
 - snps,pbl		Programmable Burst Length
 - snps,fixed-burst	Program the DMA to use the fixed burst mode
 - snps,mixed-burst	Program the DMA to use the mixed burst mode
+- snps,force_thresh_dma_mode	Force DMA to use the threshold mode for
+				both tx and rx
+- snps,force_sf_dma_mode	Force DMA to use the Store and Forward
+				mode for both tx and rx. This flag is
+				ignored if force_thresh_dma_mode is set.
 
 Optional properties:
 - mac-address: 6 bytes, mac address

Documentation/networking/00-INDEX

@@ -124,6 +124,8 @@ multiqueue.txt
 	- HOWTO for multiqueue network device support.
 netconsole.txt
 	- The network console module netconsole.ko: configuration and notes.
+netdev-FAQ.txt
+	- FAQ describing how to submit net changes to netdev mailing list.
 netdev-features.txt
 	- Network interface features API description.
 netdevices.txt

Documentation/networking/e100.txt

@@ -1,7 +1,7 @@
 Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
 ==============================================================
 
-November 15, 2005
+March 15, 2011
 
 Contents
 ========
@@ -122,7 +122,7 @@ Additional Configurations
   NOTE: This setting is not saved across reboots.
 
 
-  Ethtool
+  ethtool
   -------
 
   The driver utilizes the ethtool interface for driver configuration and

Documentation/networking/e1000.txt

@@ -1,8 +1,8 @@
-Linux* Base Driver for the Intel(R) PRO/1000 Family of Adapters
-===============================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -420,15 +420,15 @@ Additional Configurations
   - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
     with the maximum Jumbo Frames size of 16128.
 
-  - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
-    loss of link.
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
 
   - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
     support Jumbo Frames. These correspond to the following product names:
      Intel(R) PRO/1000 Gigabit Server Adapter
      Intel(R) PRO/1000 PM Network Connection
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool

Documentation/networking/e1000e.txt

@@ -1,8 +1,8 @@
-Linux* Driver for Intel(R) Network Connection
-=============================================
+Linux* Driver for Intel(R) Ethernet Network Connection
+======================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -259,13 +259,16 @@ Additional Configurations
   - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
     with the maximum Jumbo Frames size of 9234 bytes.
 
-  - Using Jumbo Frames at 10 or 100 Mbps is not supported and may result in
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
     poor performance or loss of link.
 
   - Some adapters limit Jumbo Frames sized packets to a maximum of
     4096 bytes and some adapters do not support Jumbo Frames.
 
-  Ethtool
+  - Jumbo Frames cannot be configured on an 82579-based Network device, if
+    MACSec is enabled on the system.
+
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  We
@@ -273,6 +276,9 @@ Additional Configurations
 
   http://ftp.kernel.org/pub/software/network/ethtool/
 
+  NOTE: When validating enable/disable tests on some parts (82578, for example)
+  you need to add a few seconds between tests when working with ethtool.
+
   Speed and Duplex
   ----------------
   Speed and Duplex are configured through the ethtool* utility. For

Documentation/networking/igb.txt

@@ -1,8 +1,8 @@
-Linux* Base Driver for Intel(R) Network Connection
-==================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -36,6 +36,53 @@ Default Value: 0
 This parameter adds support for SR-IOV.  It causes the driver to spawn up to
 max_vfs worth of virtual function.
 
+QueuePairs
+----------
+Valid Range:  0-1
+Default Value:  1 (TX and RX will be paired onto one interrupt vector)
+
+If set to 0, when MSI-X is enabled, the TX and RX will attempt to occupy
+separate vectors.
+
+This option can be overridden to 1 if there are not sufficient interrupts
+available.  This can occur if any combination of RSS, VMDQ, and max_vfs
+results in more than 4 queues being used.
+
+Node
+----
+Valid Range:   0-n
+Default Value: -1 (off)
+
+  0 - n: where n is the number of the NUMA node that should be used to
+         allocate memory for this adapter port.
+  -1: uses the driver default of allocating memory on whichever processor is
+      running insmod/modprobe.
+
+  The Node parameter will allow you to pick which NUMA node you want to have
+  the adapter allocate memory from.  All driver structures, in-memory queues,
+  and receive buffers will be allocated on the node specified.  This parameter
+  is only useful when interrupt affinity is specified, otherwise some portion
+  of the time the interrupt could run on a different core than the memory is
+  allocated on, causing slower memory access and impacting throughput, CPU, or
+  both.
+
+EEE
+---
+Valid Range:  0-1
+Default Value: 1 (enabled)
+
+  A link between two EEE-compliant devices will result in periodic bursts of
+  data followed by long periods where in the link is in an idle state. This Low
+  Power Idle (LPI) state is supported in both 1Gbps and 100Mbps link speeds.
+  NOTE: EEE support requires autonegotiation.
+
+DMAC
+----
+Valid Range: 0-1
+Default Value: 1 (enabled)
+  Enables or disables DMA Coalescing feature.
+
+
 
 Additional Configurations
 =========================
@@ -55,10 +102,10 @@ Additional Configurations
   - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
     with the maximum Jumbo Frames size of 9234 bytes.
 
-  - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
-    loss of link.
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information. The latest
@@ -106,6 +153,14 @@ Additional Configurations
 
   Where n=the VF that attempted to do the spoofing.
 
+  Setting MAC Address, VLAN and Rate Limit Using IProute2 Tool
+  ------------------------------------------------------------
+  You can set a MAC address of a Virtual Function (VF), a default VLAN and the
+  rate limit using the IProute2 tool. Download the latest version of the
+  iproute2 tool from Sourceforge if your version does not have all the
+  features you require.
+
+
 Support
 =======
 

Documentation/networking/igbvf.txt

@@ -1,8 +1,8 @@
-Linux* Base Driver for Intel(R) Network Connection
-==================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -55,7 +55,7 @@ networking link on the left to search for your adapter:
 Additional Configurations
 =========================
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool

Documentation/networking/ip-sysctl.txt

@@ -440,6 +440,10 @@ tcp_syncookies - BOOLEAN
 	SYN flood warnings in logs not being really flooded, your server
 	is seriously misconfigured.
 
+	If you want to test which effects syncookies have to your
+	network connections you can set this knob to 2 to enable
+	unconditionally generation of syncookies.
+
 tcp_fastopen - INTEGER
 	Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data
 	in the opening SYN packet. To use this feature, the client application
@@ -478,6 +482,15 @@ tcp_syn_retries - INTEGER
 tcp_timestamps - BOOLEAN
 	Enable timestamps as defined in RFC1323.
 
+tcp_min_tso_segs - INTEGER
+	Minimal number of segments per TSO frame.
+	Since linux-3.12, TCP does an automatic sizing of TSO frames,
+	depending on flow rate, instead of filling 64Kbytes packets.
+	For specific usages, it's possible to force TCP to build big
+	TSO frames. Note that TCP stack might split too big TSO packets
+	if available window is too small.
+	Default: 2
+
 tcp_tso_win_divisor - INTEGER
 	This allows control over what percentage of the congestion window
 	can be consumed by a single TSO frame.
@@ -516,6 +529,19 @@ tcp_wmem - vector of 3 INTEGERs: min, default, max
 	this value is ignored.
 	Default: between 64K and 4MB, depending on RAM size.
 
+tcp_notsent_lowat - UNSIGNED INTEGER
+	A TCP socket can control the amount of unsent bytes in its write queue,
+	thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll()
+	reports POLLOUT events if the amount of unsent bytes is below a per
+	socket value, and if the write queue is not full. sendmsg() will
+	also not add new buffers if the limit is hit.
+
+	This global variable controls the amount of unsent data for
+	sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change
+	to the global variable has immediate effect.
+
+	Default: UINT_MAX (0xFFFFFFFF)
+
 tcp_workaround_signed_windows - BOOLEAN
 	If set, assume no receipt of a window scaling option means the
 	remote TCP is broken and treats the window as a signed quantity.
@@ -1022,7 +1048,15 @@ disable_policy - BOOLEAN
 disable_xfrm - BOOLEAN
 	Disable IPSEC encryption on this interface, whatever the policy
 
+igmpv2_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	IGMPv1 or IGMPv2 report retransmit will take place.
+	Default: 10000 (10 seconds)
 
+igmpv3_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	IGMPv3 report retransmit will take place.
+	Default: 1000 (1 seconds)
 
 tag - INTEGER
 	Allows you to write a number, which can be used as required.
@@ -1314,6 +1348,27 @@ ndisc_notify - BOOLEAN
 	1 - Generate unsolicited neighbour advertisements when device is brought
 	    up or hardware address changes.
 
+mldv1_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	MLDv1 report retransmit will take place.
+	Default: 10000 (10 seconds)
+
+mldv2_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	MLDv2 report retransmit will take place.
+	Default: 1000 (1 second)
+
+force_mld_version - INTEGER
+	0 - (default) No enforcement of a MLD version, MLDv1 fallback allowed
+	1 - Enforce to use MLD version 1
+	2 - Enforce to use MLD version 2
+
+suppress_frag_ndisc - INTEGER
+	Control RFC 6980 (Security Implications of IPv6 Fragmentation
+	with IPv6 Neighbor Discovery) behavior:
+	1 - (default) discard fragmented neighbor discovery packets
+	0 - allow fragmented neighbor discovery packets
+
 icmp/*:
 ratelimit - INTEGER
 	Limit the maximal rates for sending ICMPv6 packets.

Documentation/networking/ixgb.txt

@@ -1,7 +1,7 @@
-Linux Base Driver for 10 Gigabit Intel(R) Network Connection
-=============================================================
+Linux Base Driver for 10 Gigabit Intel(R) Ethernet Network Connection
+=====================================================================
 
-October 9, 2007
+March 14, 2011
 
 
 Contents
@@ -274,9 +274,9 @@ Additional Configurations
   -------------------------------------------------
   Configuring a network driver to load properly when the system is started is
   distribution dependent. Typically, the configuration process involves adding
-  an alias line to files in /etc/modprobe.d/ as well as editing other system
-  startup scripts and/or configuration files.  Many popular Linux distributions
-  ship with tools to make these changes for you.  To learn the proper way to
+  an alias line to /etc/modprobe.conf as well as editing other system startup
+  scripts and/or configuration files.  Many popular Linux distributions ship
+  with tools to make these changes for you.  To learn the proper way to
   configure a network device for your system, refer to your distribution
   documentation.  If during this process you are asked for the driver or module
   name, the name for the Linux Base Driver for the Intel 10GbE Family of
@@ -306,7 +306,7 @@ Additional Configurations
   with the maximum Jumbo Frames size of 16128.
 
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool

Documentation/networking/ixgbe.txt

@@ -1,8 +1,9 @@
-Linux Base Driver for 10 Gigabit PCI Express Intel(R) Network Connection
-========================================================================
+Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Family of
+Adapters
+=============================================================================
 
-Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -16,8 +17,8 @@ Contents
 Identifying Your Adapter
 ========================
 
-The driver in this release is compatible with 82598 and 82599-based Intel
-Network Connections.
+The driver in this release is compatible with 82598, 82599 and X540-based
+Intel Network Connections.
 
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
@@ -72,7 +73,7 @@ cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
 Laser turns off for SFP+ when ifconfig down
 -------------------------------------------
 "ifconfig down" turns off the laser for 82599-based SFP+ fiber adapters.
-"ifconfig up" turns on the later.
+"ifconfig up" turns on the laser.
 
 
 82598-BASED ADAPTERS
@@ -118,6 +119,93 @@ NOTE: For 82598 backplane cards entering 1 gig mode, flow control default
 behavior is changed to off.  Flow control in 1 gig mode on these devices can
 lead to Tx hangs.
 
+Intel(R) Ethernet Flow Director
+-------------------------------
+Supports advanced filters that direct receive packets by their flows to
+different queues. Enables tight control on routing a flow in the platform.
+Matches flows and CPU cores for flow affinity. Supports multiple parameters
+for flexible flow classification and load balancing.
+
+Flow director is enabled only if the kernel is multiple TX queue capable.
+
+An included script (set_irq_affinity.sh) automates setting the IRQ to CPU
+affinity.
+
+You can verify that the driver is using Flow Director by looking at the counter
+in ethtool: fdir_miss and fdir_match.
+
+Other ethtool Commands:
+To enable Flow Director
+	ethtool -K ethX ntuple on
+To add a filter
+	Use -U switch. e.g., ethtool -U ethX flow-type tcp4 src-ip 0x178000a
+        action 1
+To see the list of filters currently present:
+	ethtool -u ethX
+
+Perfect Filter: Perfect filter is an interface to load the filter table that
+funnels all flow into queue_0 unless an alternative queue is specified using
+"action". In that case, any flow that matches the filter criteria will be
+directed to the appropriate queue.
+
+If the queue is defined as -1, filter will drop matching packets.
+
+To account for filter matches and misses, there are two stats in ethtool:
+fdir_match and fdir_miss. In addition, rx_queue_N_packets shows the number of
+packets processed by the Nth queue.
+
+NOTE: Receive Packet Steering (RPS) and Receive Flow Steering (RFS) are not
+compatible with Flow Director. IF Flow Director is enabled, these will be
+disabled.
+
+The following three parameters impact Flow Director.
+
+FdirMode
+--------
+Valid Range: 0-2 (0=off, 1=ATR, 2=Perfect filter mode)
+Default Value: 1
+
+  Flow Director filtering modes.
+
+FdirPballoc
+-----------
+Valid Range: 0-2 (0=64k, 1=128k, 2=256k)
+Default Value: 0
+
+  Flow Director allocated packet buffer size.
+
+AtrSampleRate
+--------------
+Valid Range: 1-100
+Default Value: 20
+
+  Software ATR Tx packet sample rate. For example, when set to 20, every 20th
+  packet, looks to see if the packet will create a new flow.
+
+Node
+----
+Valid Range:   0-n
+Default Value: 1 (off)
+
+  0 - n: where n is the number of NUMA nodes (i.e. 0 - 3) currently online in
+  your system
+  1: turns this option off
+
+  The Node parameter will allow you to pick which NUMA node you want to have
+  the adapter allocate memory on.
+
+max_vfs
+-------
+Valid Range:   1-63
+Default Value: 0
+
+  If the value is greater than 0 it will also force the VMDq parameter to be 1
+  or more.
+
+  This parameter adds support for SR-IOV.  It causes the driver to spawn up to
+  max_vfs worth of virtual function.
+
+
 Additional Configurations
 =========================
 
@@ -221,9 +309,10 @@ http://www.redhat.com/promo/summit/2008/downloads/pdf/Thursday/Mark_Wagner.pdf
 Known Issues
 ============
 
-  Enabling SR-IOV in a 32-bit Microsoft* Windows* Server 2008 Guest OS using
-  Intel (R) 82576-based GbE or Intel (R) 82599-based 10GbE controller under KVM
-  -----------------------------------------------------------------------------
+  Enabling SR-IOV in a 32-bit or 64-bit Microsoft* Windows* Server 2008/R2
+  Guest OS using Intel (R) 82576-based GbE or Intel (R) 82599-based 10GbE
+  controller under KVM
+  ------------------------------------------------------------------------
   KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM.  This
   includes traditional PCIe devices, as well as SR-IOV-capable devices using
   Intel 82576-based and 82599-based controllers.

Documentation/networking/ixgbevf.txt

@@ -1,8 +1,8 @@
-Linux* Base Driver for Intel(R) Network Connection
-==================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========

Documentation/networking/netdev-FAQ.txt

@@ -0,0 +1,224 @@
+
+Information you need to know about netdev
+-----------------------------------------
+
+Q: What is netdev?
+
+A: It is a mailing list for all network related linux stuff.  This includes
+   anything found under net/  (i.e. core code like IPv6) and drivers/net
+   (i.e. hardware specific drivers) in the linux source tree.
+
+   Note that some subsystems (e.g. wireless drivers) which have a high volume
+   of traffic have their own specific mailing lists.
+
+   The netdev list is managed (like many other linux mailing lists) through
+   VGER ( http://vger.kernel.org/ ) and archives can be found below:
+
+	http://marc.info/?l=linux-netdev
+	http://www.spinics.net/lists/netdev/
+
+   Aside from subsystems like that mentioned above, all network related linux
+   development (i.e. RFC, review, comments, etc) takes place on netdev.
+
+Q: How do the changes posted to netdev make their way into linux?
+
+A: There are always two trees (git repositories) in play.  Both are driven
+   by David Miller, the main network maintainer.  There is the "net" tree,
+   and the "net-next" tree.  As you can probably guess from the names, the
+   net tree is for fixes to existing code already in the mainline tree from
+   Linus, and net-next is where the new code goes for the future release.
+   You can find the trees here:
+
+	http://git.kernel.org/?p=linux/kernel/git/davem/net.git
+	http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git
+
+Q: How often do changes from these trees make it to the mainline Linus tree?
+
+A: To understand this, you need to know a bit of background information
+   on the cadence of linux development.  Each new release starts off with
+   a two week "merge window" where the main maintainers feed their new
+   stuff to Linus for merging into the mainline tree.  After the two weeks,
+   the merge window is closed, and it is called/tagged "-rc1".  No new
+   features get mainlined after this -- only fixes to the rc1 content
+   are expected.  After roughly a week of collecting fixes to the rc1
+   content, rc2 is released.  This repeats on a roughly weekly basis
+   until rc7 (typically; sometimes rc6 if things are quiet, or rc8 if
+   things are in a state of churn), and a week after the last vX.Y-rcN
+   was done, the official "vX.Y" is released.
+
+   Relating that to netdev:  At the beginning of the 2 week merge window,
+   the net-next tree will be closed - no new changes/features.  The
+   accumulated new content of the past ~10 weeks will be passed onto
+   mainline/Linus via a pull request for vX.Y -- at the same time,
+   the "net" tree will start accumulating fixes for this pulled content
+   relating to vX.Y
+
+   An announcement indicating when net-next has been closed is usually
+   sent to netdev, but knowing the above, you can predict that in advance.
+
+   IMPORTANT:  Do not send new net-next content to netdev during the
+   period during which net-next tree is closed.
+
+   Shortly after the two weeks have passed, (and vX.Y-rc1 is released) the
+   tree for net-next reopens to collect content for the next (vX.Y+1) release.
+
+   If you aren't subscribed to netdev and/or are simply unsure if net-next
+   has re-opened yet, simply check the net-next git repository link above for
+   any new networking related commits.
+
+   The "net" tree continues to collect fixes for the vX.Y content, and
+   is fed back to Linus at regular (~weekly) intervals.  Meaning that the
+   focus for "net" is on stablilization and bugfixes.
+
+   Finally, the vX.Y gets released, and the whole cycle starts over.
+
+Q: So where are we now in this cycle?
+
+A: Load the mainline (Linus) page here:
+
+	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git
+
+   and note the top of the "tags" section.  If it is rc1, it is early
+   in the dev cycle.  If it was tagged rc7 a week ago, then a release
+   is probably imminent.
+
+Q: How do I indicate which tree (net vs. net-next) my patch should be in?
+
+A: Firstly, think whether you have a bug fix or new "next-like" content.
+   Then once decided, assuming that you use git, use the prefix flag, i.e.
+
+	git format-patch --subject-prefix='PATCH net-next' start..finish
+
+   Use "net" instead of "net-next" (always lower case) in the above for
+   bug-fix net content.  If you don't use git, then note the only magic in
+   the above is just the subject text of the outgoing e-mail, and you can
+   manually change it yourself with whatever MUA you are comfortable with.
+
+Q: I sent a patch and I'm wondering what happened to it.  How can I tell
+   whether it got merged?
+
+A: Start by looking at the main patchworks queue for netdev:
+
+	http://patchwork.ozlabs.org/project/netdev/list/
+
+   The "State" field will tell you exactly where things are at with
+   your patch.
+
+Q: The above only says "Under Review".  How can I find out more?
+
+A: Generally speaking, the patches get triaged quickly (in less than 48h).
+   So be patient.  Asking the maintainer for status updates on your
+   patch is a good way to ensure your patch is ignored or pushed to
+   the bottom of the priority list.
+
+Q: How can I tell what patches are queued up for backporting to the
+   various stable releases?
+
+A: Normally Greg Kroah-Hartman collects stable commits himself, but
+   for networking, Dave collects up patches he deems critical for the
+   networking subsystem, and then hands them off to Greg.
+
+   There is a patchworks queue that you can see here:
+	http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
+
+   It contains the patches which Dave has selected, but not yet handed
+   off to Greg.  If Greg already has the patch, then it will be here:
+	http://git.kernel.org/cgit/linux/kernel/git/stable/stable-queue.git
+
+   A quick way to find whether the patch is in this stable-queue is
+   to simply clone the repo, and then git grep the mainline commit ID, e.g.
+
+	stable-queue$ git grep -l 284041ef21fdf2e
+	releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+	releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+	releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+	stable/stable-queue$
+
+Q: I see a network patch and I think it should be backported to stable.
+   Should I request it via "stable@vger.kernel.org" like the references in
+   the kernel's Documentation/stable_kernel_rules.txt file say?
+
+A: No, not for networking.  Check the stable queues as per above 1st to see
+   if it is already queued.  If not, then send a mail to netdev, listing
+   the upstream commit ID and why you think it should be a stable candidate.
+
+   Before you jump to go do the above, do note that the normal stable rules
+   in Documentation/stable_kernel_rules.txt still apply.  So you need to
+   explicitly indicate why it is a critical fix and exactly what users are
+   impacted.  In addition, you need to convince yourself that you _really_
+   think it has been overlooked, vs. having been considered and rejected.
+
+   Generally speaking, the longer it has had a chance to "soak" in mainline,
+   the better the odds that it is an OK candidate for stable.  So scrambling
+   to request a commit be added the day after it appears should be avoided.
+
+Q: I have created a network patch and I think it should be backported to
+   stable.  Should I add a "Cc: stable@vger.kernel.org" like the references
+   in the kernel's Documentation/ directory say?
+
+A: No.  See above answer.  In short, if you think it really belongs in
+   stable, then ensure you write a decent commit log that describes who
+   gets impacted by the bugfix and how it manifests itself, and when the
+   bug was introduced.  If you do that properly, then the commit will
+   get handled appropriately and most likely get put in the patchworks
+   stable queue if it really warrants it.
+
+   If you think there is some valid information relating to it being in
+   stable that does _not_ belong in the commit log, then use the three
+   dash marker line as described in Documentation/SubmittingPatches to
+   temporarily embed that information into the patch that you send.
+
+Q: Someone said that the comment style and coding convention is different
+   for the networking content.  Is this true?
+
+A: Yes, in a largely trivial way.  Instead of this:
+
+	/*
+	 * foobar blah blah blah
+	 * another line of text
+	 */
+
+   it is requested that you make it look like this:
+
+	/* foobar blah blah blah
+	 * another line of text
+	 */
+
+Q: I am working in existing code that has the former comment style and not the
+   latter.  Should I submit new code in the former style or the latter?
+
+A: Make it the latter style, so that eventually all code in the domain of
+   netdev is of this format.
+
+Q: I found a bug that might have possible security implications or similar.
+   Should I mail the main netdev maintainer off-list?
+
+A: No. The current netdev maintainer has consistently requested that people
+   use the mailing lists and not reach out directly.  If you aren't OK with
+   that, then perhaps consider mailing "security@kernel.org" or reading about
+   http://oss-security.openwall.org/wiki/mailing-lists/distros
+   as possible alternative mechanisms.
+
+Q: What level of testing is expected before I submit my change?
+
+A: If your changes are against net-next, the expectation is that you
+   have tested by layering your changes on top of net-next.  Ideally you
+   will have done run-time testing specific to your change, but at a
+   minimum, your changes should survive an "allyesconfig" and an
+   "allmodconfig" build without new warnings or failures.
+
+Q: Any other tips to help ensure my net/net-next patch gets OK'd?
+
+A: Attention to detail.  Re-read your own work as if you were the
+   reviewer.  You can start with using checkpatch.pl, perhaps even
+   with the "--strict" flag.  But do not be mindlessly robotic in
+   doing so.  If your change is a bug-fix, make sure your commit log
+   indicates the end-user visible symptom, the underlying reason as
+   to why it happens, and then if necessary, explain why the fix proposed
+   is the best way to get things done.   Don't mangle whitespace, and as
+   is common, don't mis-indent function arguments that span multiple lines.
+   If it is your 1st patch, mail it to yourself so you can test apply
+   it to an unpatched tree to confirm infrastructure didn't mangle it.
+
+   Finally, go back and read Documentation/SubmittingPatches to be
+   sure you are not repeating some common mistake documented there.

Documentation/networking/openvswitch.txt

@@ -91,6 +91,46 @@ Often we ellipsize arguments not important to the discussion, e.g.:
     in_port(1), eth(...), eth_type(0x0800), ipv4(...), tcp(...)
 
 
+Wildcarded flow key format
+--------------------------
+
+A wildcarded flow is described with two sequences of Netlink attributes
+passed over the Netlink socket. A flow key, exactly as described above, and an
+optional corresponding flow mask.
+
+A wildcarded flow can represent a group of exact match flows. Each '1' bit
+in the mask specifies a exact match with the corresponding bit in the flow key.
+A '0' bit specifies a don't care bit, which will match either a '1' or '0' bit
+of a incoming packet. Using wildcarded flow can improve the flow set up rate
+by reduce the number of new flows need to be processed by the user space program.
+
+Support for the mask Netlink attribute is optional for both the kernel and user
+space program. The kernel can ignore the mask attribute, installing an exact
+match flow, or reduce the number of don't care bits in the kernel to less than
+what was specified by the user space program. In this case, variations in bits
+that the kernel does not implement will simply result in additional flow setups.
+The kernel module will also work with user space programs that neither support
+nor supply flow mask attributes.
+
+Since the kernel may ignore or modify wildcard bits, it can be difficult for
+the userspace program to know exactly what matches are installed. There are
+two possible approaches: reactively install flows as they miss the kernel
+flow table (and therefore not attempt to determine wildcard changes at all)
+or use the kernel's response messages to determine the installed wildcards.
+
+When interacting with userspace, the kernel should maintain the match portion
+of the key exactly as originally installed. This will provides a handle to
+identify the flow for all future operations. However, when reporting the
+mask of an installed flow, the mask should include any restrictions imposed
+by the kernel.
+
+The behavior when using overlapping wildcarded flows is undefined. It is the
+responsibility of the user space program to ensure that any incoming packet
+can match at most one flow, wildcarded or not. The current implementation
+performs best-effort detection of overlapping wildcarded flows and may reject
+some but not all of them. However, this behavior may change in future versions.
+
+
 Basic rule for evolving flow keys
 ---------------------------------
 

Documentation/networking/packet_mmap.txt

@@ -543,6 +543,14 @@ TPACKET_V2 --> TPACKET_V3:
 In the AF_PACKET fanout mode, packet reception can be load balanced among
 processes. This also works in combination with mmap(2) on packet sockets.
 
+Currently implemented fanout policies are:
+
+  - PACKET_FANOUT_HASH: schedule to socket by skb's rxhash
+  - PACKET_FANOUT_LB: schedule to socket by round-robin
+  - PACKET_FANOUT_CPU: schedule to socket by CPU packet arrives on
+  - PACKET_FANOUT_RND: schedule to socket by random selection
+  - PACKET_FANOUT_ROLLOVER: if one socket is full, rollover to another
+
 Minimal example code by David S. Miller (try things like "./test eth0 hash",
 "./test eth0 lb", etc.):
 

Documentation/networking/sctp.txt

@@ -19,7 +19,6 @@ of SCTP that is RFC 2960 compliant and provides an programming interface
 referred to as the  UDP-style API of the Sockets Extensions for SCTP, as 
 proposed in IETF Internet-Drafts.    
 
-
 Caveats:  
 
 -lksctp can be built as statically or as a module.  However, be aware that 
@@ -33,6 +32,4 @@ For more information, please visit the lksctp project website:
    http://www.sf.net/projects/lksctp
 
 Or contact the lksctp developers through the mailing list:
-   <lksctp-developers@lists.sourceforge.net> 
-
-
+   <linux-sctp@vger.kernel.org>

Documentation/networking/stmmac.txt

@@ -123,6 +123,7 @@ struct plat_stmmacenet_data {
 	int bugged_jumbo;
 	int pmt;
 	int force_sf_dma_mode;
+	int force_thresh_dma_mode;
 	int riwt_off;
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	void (*bus_setup)(void __iomem *ioaddr);
@@ -159,6 +160,8 @@ Where:
  o pmt: core has the embedded power module (optional).
  o force_sf_dma_mode: force DMA to use the Store and Forward mode
 		     instead of the Threshold.
+ o force_thresh_dma_mode: force DMA to use the Shreshold mode other than
+		     the Store and Forward mode.
  o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
  o fix_mac_speed: this callback is used for modifying some syscfg registers
 		 (on ST SoCs) according to the link speed negotiated by the

Documentation/networking/tproxy.txt

@@ -2,9 +2,8 @@ Transparent proxy support
 =========================
 
 This feature adds Linux 2.2-like transparent proxy support to current kernels.
-To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in
-your kernel config. You will need policy routing too, so be sure to enable that
-as well.
+To use it, enable the socket match and the TPROXY target in your kernel config.
+You will need policy routing too, so be sure to enable that as well.
 
 
 1. Making non-local sockets work

Documentation/sysctl/net.txt

@@ -50,6 +50,19 @@ The maximum number of packets that kernel can handle on a NAPI interrupt,
 it's a Per-CPU variable.
 Default: 64
 
+default_qdisc
+--------------
+
+The default queuing discipline to use for network devices. This allows
+overriding the default queue discipline of pfifo_fast with an
+alternative. Since the default queuing discipline is created with the
+no additional parameters so is best suited to queuing disciplines that
+work well without configuration like stochastic fair queue (sfq),
+CoDel (codel) or fair queue CoDel (fq_codel). Don't use queuing disciplines
+like Hierarchical Token Bucket or Deficit Round Robin which require setting
+up classes and bandwidths.
+Default: pfifo_fast
+
 busy_read
 ----------------
 Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL)

MAINTAINERS

@@ -2108,7 +2108,8 @@ F:	drivers/usb/chipidea/
 
 CISCO VIC ETHERNET NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
-M:	Roopa Prabhu <roprabhu@cisco.com>
+M:	Sujith Sankar <ssujith@cisco.com>
+M:	Govindarajulu Varadarajan <govindarajulu90@gmail.com>
 M:	Neel Patel <neepatel@cisco.com>
 M:	Nishank Trivedi <nistrive@cisco.com>
 S:	Supported
@@ -4404,7 +4405,7 @@ F:	drivers/net/wireless/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
 M:	Johannes Berg <johannes.berg@intel.com>
-M:	Wey-Yi Guy <wey-yi.w.guy@intel.com>
+M:	Emmanuel Grumbach <emmanuel.grumbach@intel.com>
 M:	Intel Linux Wireless <ilw@linux.intel.com>
 L:	linux-wireless@vger.kernel.org
 W:	http://intellinuxwireless.org
@@ -5831,7 +5832,7 @@ M:	Aloisio Almeida Jr <aloisio.almeida@openbossa.org>
 M:	Samuel Ortiz <sameo@linux.intel.com>
 L:	linux-wireless@vger.kernel.org
 L:	linux-nfc@lists.01.org (moderated for non-subscribers)
-S:	Maintained
+S:	Supported
 F:	net/nfc/
 F:	include/net/nfc/
 F:	include/uapi/linux/nfc.h
@@ -7274,6 +7275,7 @@ W:	http://lksctp.sourceforge.net
 S:	Maintained
 F:	Documentation/networking/sctp.txt
 F:	include/linux/sctp.h
+F:	include/uapi/linux/sctp.h
 F:	include/net/sctp/
 F:	net/sctp/
 
@@ -8022,6 +8024,12 @@ F:	arch/m68k/sun3*/
 F:	arch/m68k/include/asm/sun3*
 F:	drivers/net/ethernet/i825xx/sun3*
 
+SUNDANCE NETWORK DRIVER
+M:	Denis Kirjanov <kda@linux-powerpc.org>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/dlink/sundance.c
+
 SUPERH
 M:	Paul Mundt <lethal@linux-sh.org>
 L:	linux-sh@vger.kernel.org

arch/arm/boot/dts/sama5d3xmb.dtsi

@@ -81,6 +81,14 @@
 
 			macb1: ethernet@f802c000 {
 				phy-mode = "rmii";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+				phy0: ethernet-phy@1 {
+					interrupt-parent = <&pioE>;
+					interrupts = <30 IRQ_TYPE_EDGE_FALLING>;
+					reg = <1>;
+				};
 			};
 
 			pinctrl@fffff200 {

arch/arm/mach-pxa/icontrol.c

@@ -73,9 +73,6 @@ static struct pxa2xx_spi_chip mcp251x_chip_info4 = {
 
 static struct mcp251x_platform_data mcp251x_info = {
 	.oscillator_frequency = 16E6,
-	.board_specific_setup = NULL,
-	.power_enable         = NULL,
-	.transceiver_enable   = NULL
 };
 
 static struct spi_board_info mcp251x_board_info[] = {

arch/arm/mach-pxa/zeus.c

@@ -29,6 +29,8 @@
 #include <linux/i2c/pca953x.h>
 #include <linux/apm-emulation.h>
 #include <linux/can/platform/mcp251x.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 
 #include <asm/mach-types.h>
 #include <asm/suspend.h>
@@ -391,33 +393,34 @@ static struct pxa2xx_spi_master pxa2xx_spi_ssp3_master_info = {
 };
 
 /* CAN bus on SPI */
-static int zeus_mcp2515_setup(struct spi_device *sdev)
-{
-	int err;
-
-	err = gpio_request(ZEUS_CAN_SHDN_GPIO, "CAN shutdown");
-	if (err)
-		return err;
+static struct regulator_consumer_supply can_regulator_consumer =
+	REGULATOR_SUPPLY("vdd", "spi3.0");
 
-	err = gpio_direction_output(ZEUS_CAN_SHDN_GPIO, 1);
-	if (err) {
-		gpio_free(ZEUS_CAN_SHDN_GPIO);
-		return err;
-	}
+static struct regulator_init_data can_regulator_init_data = {
+	.constraints	= {
+		.valid_ops_mask	= REGULATOR_CHANGE_STATUS,
+	},
+	.consumer_supplies	= &can_regulator_consumer,
+	.num_consumer_supplies	= 1,
+};
 
-	return 0;
-}
+static struct fixed_voltage_config can_regulator_pdata = {
+	.supply_name	= "CAN_SHDN",
+	.microvolts	= 3300000,
+	.gpio		= ZEUS_CAN_SHDN_GPIO,
+	.init_data	= &can_regulator_init_data,
+};
 
-static int zeus_mcp2515_transceiver_enable(int enable)
-{
-	gpio_set_value(ZEUS_CAN_SHDN_GPIO, !enable);
-	return 0;
-}
+static struct platform_device can_regulator_device = {
+	.name	= "reg-fixed-volage",
+	.id	= -1,
+	.dev	= {
+		.platform_data	= &can_regulator_pdata,
+	},
+};
 
 static struct mcp251x_platform_data zeus_mcp2515_pdata = {
 	.oscillator_frequency	= 16*1000*1000,
-	.board_specific_setup	= zeus_mcp2515_setup,
-	.power_enable		= zeus_mcp2515_transceiver_enable,
 };
 
 static struct spi_board_info zeus_spi_board_info[] = {
@@ -516,6 +519,7 @@ static struct platform_device *zeus_devices[] __initdata = {
 	&zeus_leds_device,
 	&zeus_pcmcia_device,
 	&zeus_max6369_device,
+	&can_regulator_device,
 };
 
 /* AC'97 */

arch/arm/mach-shmobile/board-armadillo800eva.c

@@ -358,7 +358,6 @@ static struct platform_device usbhsf_device = {
 static struct sh_eth_plat_data sh_eth_platdata = {
 	.phy			= 0x00, /* LAN8710A */
 	.edmac_endian		= EDMAC_LITTLE_ENDIAN,
-	.register_type		= SH_ETH_REG_GIGABIT,
 	.phy_interface		= PHY_INTERFACE_MODE_MII,
 };
 

arch/arm/mach-shmobile/board-bockw.c

@@ -91,7 +91,6 @@ static struct sh_mobile_sdhi_info sdhi0_info = {
 static struct sh_eth_plat_data ether_platform_data __initdata = {
 	.phy		= 0x01,
 	.edmac_endian	= EDMAC_LITTLE_ENDIAN,
-	.register_type	= SH_ETH_REG_FAST_RCAR,
 	.phy_interface	= PHY_INTERFACE_MODE_RMII,
 	/*
 	 * Although the LINK signal is available on the board, it's connected to

arch/sh/boards/board-espt.c

@@ -80,7 +80,6 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 0,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 

arch/sh/boards/board-sh7757lcr.c

@@ -77,7 +77,6 @@ static struct resource sh_eth0_resources[] = {
 static struct sh_eth_plat_data sh7757_eth0_pdata = {
 	.phy = 1,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_FAST_SH4,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -106,7 +105,6 @@ static struct resource sh_eth1_resources[] = {
 static struct sh_eth_plat_data sh7757_eth1_pdata = {
 	.phy = 1,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_FAST_SH4,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -151,7 +149,6 @@ static struct resource sh_eth_giga0_resources[] = {
 static struct sh_eth_plat_data sh7757_eth_giga0_pdata = {
 	.phy = 18,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
@@ -186,7 +183,6 @@ static struct resource sh_eth_giga1_resources[] = {
 static struct sh_eth_plat_data sh7757_eth_giga1_pdata = {
 	.phy = 19,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };

arch/sh/boards/mach-ecovec24/setup.c

@@ -159,7 +159,6 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8700 */
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_FAST_SH4,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 	.ether_link_active_low = 1
 };

arch/sh/boards/mach-se/7724/setup.c

@@ -365,7 +365,7 @@ static struct platform_device keysc_device = {
 static struct resource sh_eth_resources[] = {
 	[0] = {
 		.start = SH_ETH_ADDR,
-		.end   = SH_ETH_ADDR + 0x1FC,
+		.end   = SH_ETH_ADDR + 0x1FC - 1,
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
@@ -377,6 +377,7 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8187 */
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
+	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
 static struct platform_device sh_eth_device = {

arch/sh/boards/mach-sh7763rdp/setup.c

@@ -88,7 +88,6 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 1,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 

arch/sh/kernel/cpu/sh2/setup-sh7619.c

@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_eth.h>
 #include <linux/sh_timer.h>
 #include <linux/io.h>
 
@@ -110,10 +111,16 @@ static struct platform_device scif2_device = {
 	},
 };
 
+static struct sh_eth_plat_data eth_platform_data = {
+	.phy		= 1,
+	.edmac_endian	= EDMAC_LITTLE_ENDIAN,
+	.phy_interface	= PHY_INTERFACE_MODE_MII,
+};
+
 static struct resource eth_resources[] = {
 	[0] = {
 		.start = 0xfb000000,
-		.end =   0xfb0001c8,
+		.end = 0xfb0001c7,
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
@@ -127,7 +134,7 @@ static struct platform_device eth_device = {
 	.name = "sh7619-ether",
 	.id = -1,
 	.dev = {
-		.platform_data = (void *)1,
+		.platform_data = &eth_platform_data,
 	},
 	.num_resources = ARRAY_SIZE(eth_resources),
 	.resource = eth_resources,

arch/tile/gxio/iorpc_mpipe.c

@@ -387,6 +387,27 @@ int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac)
 
 EXPORT_SYMBOL(gxio_mpipe_link_close_aux);
 
+struct link_set_attr_aux_param {
+	int mac;
+	uint32_t attr;
+	int64_t val;
+};
+
+int gxio_mpipe_link_set_attr_aux(gxio_mpipe_context_t * context, int mac,
+				 uint32_t attr, int64_t val)
+{
+	struct link_set_attr_aux_param temp;
+	struct link_set_attr_aux_param *params = &temp;
+
+	params->mac = mac;
+	params->attr = attr;
+	params->val = val;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params), GXIO_MPIPE_OP_LINK_SET_ATTR_AUX);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_link_set_attr_aux);
 
 struct get_timestamp_aux_param {
 	uint64_t sec;
@@ -454,6 +475,51 @@ int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context,
 
 EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_aux);
 
+struct adjust_timestamp_freq_param {
+	int32_t ppb;
+};
+
+int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t * context,
+				     int32_t ppb)
+{
+	struct adjust_timestamp_freq_param temp;
+	struct adjust_timestamp_freq_param *params = &temp;
+
+	params->ppb = ppb;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params),
+			     GXIO_MPIPE_OP_ADJUST_TIMESTAMP_FREQ);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_freq);
+
+struct config_edma_ring_blks_param {
+	unsigned int ering;
+	unsigned int max_blks;
+	unsigned int min_snf_blks;
+	unsigned int db;
+};
+
+int gxio_mpipe_config_edma_ring_blks(gxio_mpipe_context_t * context,
+				     unsigned int ering, unsigned int max_blks,
+				     unsigned int min_snf_blks, unsigned int db)
+{
+	struct config_edma_ring_blks_param temp;
+	struct config_edma_ring_blks_param *params = &temp;
+
+	params->ering = ering;
+	params->max_blks = max_blks;
+	params->min_snf_blks = min_snf_blks;
+	params->db = db;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params),
+			     GXIO_MPIPE_OP_CONFIG_EDMA_RING_BLKS);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_config_edma_ring_blks);
+
 struct arm_pollfd_param {
 	union iorpc_pollfd pollfd;
 };

arch/tile/gxio/iorpc_mpipe_info.c

@@ -16,6 +16,24 @@
 #include "gxio/iorpc_mpipe_info.h"
 
 
+struct instance_aux_param {
+	_gxio_mpipe_link_name_t name;
+};
+
+int gxio_mpipe_info_instance_aux(gxio_mpipe_info_context_t * context,
+				 _gxio_mpipe_link_name_t name)
+{
+	struct instance_aux_param temp;
+	struct instance_aux_param *params = &temp;
+
+	params->name = name;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params), GXIO_MPIPE_INFO_OP_INSTANCE_AUX);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_info_instance_aux);
+
 struct enumerate_aux_param {
 	_gxio_mpipe_link_name_t name;
 	_gxio_mpipe_link_mac_t mac;

arch/tile/gxio/mpipe.c

@@ -36,8 +36,14 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
 	int fd;
 	int i;
 
+	if (mpipe_index >= GXIO_MPIPE_INSTANCE_MAX)
+		return -EINVAL;
+
 	snprintf(file, sizeof(file), "mpipe/%d/iorpc", mpipe_index);
 	fd = hv_dev_open((HV_VirtAddr) file, 0);
+
+	context->fd = fd;
+
 	if (fd < 0) {
 		if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX)
 			return fd;
@@ -45,8 +51,6 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
 			return -ENODEV;
 	}
 
-	context->fd = fd;
-
 	/* Map in the MMIO space. */
 	context->mmio_cfg_base = (void __force *)
 		iorpc_ioremap(fd, HV_MPIPE_CONFIG_MMIO_OFFSET,
@@ -64,12 +68,15 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
 	for (i = 0; i < 8; i++)
 		context->__stacks.stacks[i] = 255;
 
+	context->instance = mpipe_index;
+
 	return 0;
 
       fast_failed:
 	iounmap((void __force __iomem *)(context->mmio_cfg_base));
       cfg_failed:
 	hv_dev_close(context->fd);
+	context->fd = -1;
 	return -ENODEV;
 }
 
@@ -383,7 +390,7 @@ EXPORT_SYMBOL_GPL(gxio_mpipe_iqueue_init);
 
 int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 			   gxio_mpipe_context_t *context,
-			   unsigned int edma_ring_id,
+			   unsigned int ering,
 			   unsigned int channel,
 			   void *mem, unsigned int mem_size,
 			   unsigned int mem_flags)
@@ -394,7 +401,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 	/* Offset used to read number of completed commands. */
 	MPIPE_EDMA_POST_REGION_ADDR_t offset;
 
-	int result = gxio_mpipe_init_edma_ring(context, edma_ring_id, channel,
+	int result = gxio_mpipe_init_edma_ring(context, ering, channel,
 					       mem, mem_size, mem_flags);
 	if (result < 0)
 		return result;
@@ -405,7 +412,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 	offset.region =
 		MPIPE_MMIO_ADDR__REGION_VAL_EDMA -
 		MPIPE_MMIO_ADDR__REGION_VAL_IDMA;
-	offset.ring = edma_ring_id;
+	offset.ring = ering;
 
 	__gxio_dma_queue_init(&equeue->dma_queue,
 			      context->mmio_fast_base + offset.word,
@@ -413,6 +420,9 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 	equeue->edescs = mem;
 	equeue->mask_num_entries = num_entries - 1;
 	equeue->log2_num_entries = __builtin_ctz(num_entries);
+	equeue->context = context;
+	equeue->ering = ering;
+	equeue->channel = channel;
 
 	return 0;
 }
@@ -493,6 +503,20 @@ static gxio_mpipe_context_t *_gxio_get_link_context(void)
 	return contextp;
 }
 
+int gxio_mpipe_link_instance(const char *link_name)
+{
+	_gxio_mpipe_link_name_t name;
+	gxio_mpipe_context_t *context = _gxio_get_link_context();
+
+	if (!context)
+		return GXIO_ERR_NO_DEVICE;
+
+	strncpy(name.name, link_name, sizeof(name.name));
+	name.name[GXIO_MPIPE_LINK_NAME_LEN - 1] = '\0';
+
+	return gxio_mpipe_info_instance_aux(context, name);
+}
+
 int gxio_mpipe_link_enumerate_mac(int idx, char *link_name, uint8_t *link_mac)
 {
 	int rv;
@@ -543,3 +567,12 @@ int gxio_mpipe_link_close(gxio_mpipe_link_t *link)
 }
 
 EXPORT_SYMBOL_GPL(gxio_mpipe_link_close);
+
+int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr,
+			     int64_t val)
+{
+	return gxio_mpipe_link_set_attr_aux(link->context, link->mac, attr,
+					    val);
+}
+
+EXPORT_SYMBOL_GPL(gxio_mpipe_link_set_attr);

arch/tile/include/gxio/iorpc_mpipe.h

@@ -44,10 +44,13 @@
 #define GXIO_MPIPE_OP_REGISTER_CLIENT_MEMORY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1210)
 #define GXIO_MPIPE_OP_LINK_OPEN_AUX    IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1211)
 #define GXIO_MPIPE_OP_LINK_CLOSE_AUX   IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1212)
+#define GXIO_MPIPE_OP_LINK_SET_ATTR_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1213)
 
-#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121e)
-#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121f)
-#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1220)
+#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x121e)
+#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x121f)
+#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1220)
+#define GXIO_MPIPE_OP_CONFIG_EDMA_RING_BLKS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1221)
+#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_FREQ IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1222)
 #define GXIO_MPIPE_OP_ARM_POLLFD       IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9000)
 #define GXIO_MPIPE_OP_CLOSE_POLLFD     IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9001)
 #define GXIO_MPIPE_OP_GET_MMIO_BASE    IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
@@ -114,6 +117,8 @@ int gxio_mpipe_link_open_aux(gxio_mpipe_context_t * context,
 
 int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac);
 
+int gxio_mpipe_link_set_attr_aux(gxio_mpipe_context_t * context, int mac,
+				 uint32_t attr, int64_t val);
 
 int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t * context, uint64_t * sec,
 				 uint64_t * nsec, uint64_t * cycles);
@@ -124,6 +129,9 @@ int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t * context, uint64_t sec,
 int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context,
 				    int64_t nsec);
 
+int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t * context,
+				     int32_t ppb);
+
 int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie);
 
 int gxio_mpipe_close_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie);

arch/tile/include/gxio/iorpc_mpipe_info.h

@@ -27,11 +27,15 @@
 #include <asm/pgtable.h>
 
 
+#define GXIO_MPIPE_INFO_OP_INSTANCE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1250)
 #define GXIO_MPIPE_INFO_OP_ENUMERATE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1251)
 #define GXIO_MPIPE_INFO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
 #define GXIO_MPIPE_INFO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001)
 
 
+int gxio_mpipe_info_instance_aux(gxio_mpipe_info_context_t * context,
+				 _gxio_mpipe_link_name_t name);
+
 int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context,
 				  unsigned int idx,
 				  _gxio_mpipe_link_name_t * name,

arch/tile/include/gxio/mpipe.h

@@ -220,6 +220,13 @@ typedef MPIPE_PDESC_t gxio_mpipe_idesc_t;
  */
 typedef MPIPE_EDMA_DESC_t gxio_mpipe_edesc_t;
 
+/*
+ * Max # of mpipe instances. 2 currently.
+ */
+#define GXIO_MPIPE_INSTANCE_MAX  HV_MPIPE_INSTANCE_MAX
+
+#define NR_MPIPE_MAX   GXIO_MPIPE_INSTANCE_MAX
+
 /* Get the "va" field from an "idesc".
  *
  * This is the address at which the ingress hardware copied the first
@@ -311,6 +318,9 @@ typedef struct {
 	/* File descriptor for calling up to Linux (and thus the HV). */
 	int fd;
 
+	/* Corresponding mpipe instance #. */
+	int instance;
+
 	/* The VA at which configuration registers are mapped. */
 	char *mmio_cfg_base;
 
@@ -810,7 +820,7 @@ extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context,
 /* Initialize an eDMA ring, using the given memory and size.
  *
  * @param context An initialized mPIPE context.
- * @param ring The eDMA ring index.
+ * @param ering The eDMA ring index.
  * @param channel The channel to use.  This must be one of the channels
  * associated with the context's set of open links.
  * @param mem A physically contiguous region of memory to be filled
@@ -823,10 +833,37 @@ extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context,
  * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure.
  */
 extern int gxio_mpipe_init_edma_ring(gxio_mpipe_context_t *context,
-				     unsigned int ring, unsigned int channel,
+				     unsigned int ering, unsigned int channel,
 				     void *mem, size_t mem_size,
 				     unsigned int mem_flags);
 
+/* Set the "max_blks", "min_snf_blks", and "db" fields of
+ * ::MPIPE_EDMA_RG_INIT_DAT_THRESH_t for a given edma ring.
+ *
+ * The global pool of dynamic blocks will be automatically adjusted.
+ *
+ * This function should not be called after any egress has been done
+ * on the edma ring.
+ *
+ * Most applications should just use gxio_mpipe_equeue_set_snf_size().
+ *
+ * @param context An initialized mPIPE context.
+ * @param ering The eDMA ring index.
+ * @param max_blks The number of blocks to dedicate to the ring
+ * (normally min_snf_blks + 1).  Must be greater than min_snf_blocks.
+ * @param min_snf_blks The number of blocks which must be stored
+ * prior to starting to send the packet (normally 12).
+ * @param db Whether to allow use of dynamic blocks by the ring
+ * (normally 1).
+ *
+ * @return 0 on success, negative on error.
+ */
+extern int gxio_mpipe_config_edma_ring_blks(gxio_mpipe_context_t *context,
+					    unsigned int ering,
+					    unsigned int max_blks,
+					    unsigned int min_snf_blks,
+					    unsigned int db);
+
 /*****************************************************************
  *                      Classifier Program                        *
  ******************************************************************/
@@ -1288,15 +1325,39 @@ typedef struct {
 	/* The log2() of the number of entries. */
 	unsigned long log2_num_entries;
 
+	/* The context. */
+	gxio_mpipe_context_t *context;
+
+	/* The ering. */
+	unsigned int ering;
+
+	/* The channel. */
+	unsigned int channel;
+
 } gxio_mpipe_equeue_t;
 
 /* Initialize an "equeue".
  *
- * Takes the equeue plus the same args as gxio_mpipe_init_edma_ring().
+ * This function uses gxio_mpipe_init_edma_ring() to initialize the
+ * underlying edma_ring using the provided arguments.
+ *
+ * @param equeue An egress queue to be initialized.
+ * @param context An initialized mPIPE context.
+ * @param ering The eDMA ring index.
+ * @param channel The channel to use.  This must be one of the channels
+ * associated with the context's set of open links.
+ * @param mem A physically contiguous region of memory to be filled
+ * with a ring of ::gxio_mpipe_edesc_t structures.
+ * @param mem_size Number of bytes in the ring.  Must be 512, 2048,
+ * 8192 or 65536, times 16 (i.e. sizeof(gxio_mpipe_edesc_t)).
+ * @param mem_flags ::gxio_mpipe_mem_flags_e memory flags.
+ *
+ * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_EDMA_RING or
+ * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure.
  */
 extern int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 				  gxio_mpipe_context_t *context,
-				  unsigned int edma_ring_id,
+				  unsigned int ering,
 				  unsigned int channel,
 				  void *mem, unsigned int mem_size,
 				  unsigned int mem_flags);
@@ -1494,6 +1555,37 @@ static inline int gxio_mpipe_equeue_is_complete(gxio_mpipe_equeue_t *equeue,
 					    completion_slot, update);
 }
 
+/* Set the snf (store and forward) size for an equeue.
+ *
+ * The snf size for an equeue defaults to 1536, and encodes the size
+ * of the largest packet for which egress is guaranteed to avoid
+ * transmission underruns and/or corrupt checksums under heavy load.
+ *
+ * The snf size affects a global resource pool which cannot support,
+ * for example, all 24 equeues each requesting an snf size of 8K.
+ *
+ * To ensure that jumbo packets can be egressed properly, the snf size
+ * should be set to the size of the largest possible packet, which
+ * will usually be limited by the size of the app's largest buffer.
+ *
+ * This is a convenience wrapper around
+ * gxio_mpipe_config_edma_ring_blks().
+ *
+ * This function should not be called after any egress has been done
+ * on the equeue.
+ *
+ * @param equeue An egress queue initialized via gxio_mpipe_equeue_init().
+ * @param size The snf size, in bytes.
+ * @return Zero on success, negative error otherwise.
+ */
+static inline int gxio_mpipe_equeue_set_snf_size(gxio_mpipe_equeue_t *equeue,
+						 size_t size)
+{
+	int blks = (size + 127) / 128;
+	return gxio_mpipe_config_edma_ring_blks(equeue->context, equeue->ering,
+						blks + 1, blks, 1);
+}
+
 /*****************************************************************
  *                        Link Management                         *
  ******************************************************************/
@@ -1634,6 +1726,24 @@ typedef struct {
 	uint8_t mac;
 } gxio_mpipe_link_t;
 
+/* Translate a link name to the instance number of the mPIPE shim which is
+ *  connected to that link.  This call does not verify whether the link is
+ *  currently available, and does not reserve any link resources;
+ *  gxio_mpipe_link_open() must be called to perform those functions.
+ *
+ *  Typically applications will call this function to translate a link name
+ *  to an mPIPE instance number; call gxio_mpipe_init(), passing it that
+ *  instance number, to initialize the mPIPE shim; and then call
+ *  gxio_mpipe_link_open(), passing it the same link name plus the mPIPE
+ *  context, to configure the link.
+ *
+ * @param link_name Name of the link; see @ref gxio_mpipe_link_names.
+ * @return The mPIPE instance number which is associated with the named
+ *  link, or a negative error code (::GXIO_ERR_NO_DEVICE) if the link does
+ *  not exist.
+ */
+extern int gxio_mpipe_link_instance(const char *link_name);
+
 /* Retrieve one of this system's legal link names, and its MAC address.
  *
  * @param index Link name index.  If a system supports N legal link names,
@@ -1697,6 +1807,17 @@ static inline int gxio_mpipe_link_channel(gxio_mpipe_link_t *link)
 	return link->channel;
 }
 
+/* Set a link attribute.
+ *
+ * @param link A properly initialized link state object.
+ * @param attr An attribute from the set of @ref gxio_mpipe_link_attrs.
+ * @param val New value of the attribute.
+ * @return 0 if the attribute was successfully set, or a negative error
+ *  code.
+ */
+extern int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr,
+				    int64_t val);
+
 ///////////////////////////////////////////////////////////////////
 //                             Timestamp                         //
 ///////////////////////////////////////////////////////////////////
@@ -1733,4 +1854,18 @@ extern int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context,
 extern int gxio_mpipe_adjust_timestamp(gxio_mpipe_context_t *context,
 				       int64_t delta);
 
+/** Adjust the mPIPE timestamp clock frequency.
+ *
+ * @param context An initialized mPIPE context.
+ * @param ppb A 32-bit signed PPB (Parts Per Billion) value to adjust.
+ * The absolute value of ppb must be less than or equal to 1000000000.
+ * Values less than about 30000 will generally cause a GXIO_ERR_INVAL
+ * return due to the granularity of the hardware that converts reference
+ * clock cycles into seconds and nanoseconds.
+ * @return If the call was successful, zero; otherwise, a negative error
+ *  code.
+ */
+extern int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t* context,
+                                            int32_t ppb);
+
 #endif /* !_GXIO_MPIPE_H_ */

arch/tile/include/hv/drv_mpipe_intf.h

@@ -23,6 +23,9 @@
 #include <arch/mpipe_constants.h>
 
 
+/** Number of mPIPE instances supported */
+#define HV_MPIPE_INSTANCE_MAX   (2)
+
 /** Number of buffer stacks (32). */
 #define HV_MPIPE_NUM_BUFFER_STACKS \
   (MPIPE_MMIO_INIT_DAT_GX36_1__BUFFER_STACK_MASK_WIDTH)

drivers/atm/he.c

@@ -1088,15 +1088,8 @@ static int he_start(struct atm_dev *dev)
 	for (i = 0; i < 6; ++i)
 		dev->esi[i] = read_prom_byte(he_dev, MAC_ADDR + i);
 
-	hprintk("%s%s, %x:%x:%x:%x:%x:%x\n",
-				he_dev->prod_id,
-					he_dev->media & 0x40 ? "SM" : "MM",
-						dev->esi[0],
-						dev->esi[1],
-						dev->esi[2],
-						dev->esi[3],
-						dev->esi[4],
-						dev->esi[5]);
+	hprintk("%s%s, %pM\n", he_dev->prod_id,
+		he_dev->media & 0x40 ? "SM" : "MM", dev->esi);
 	he_dev->atm_dev->link_rate = he_is622(he_dev) ?
 						ATM_OC12_PCR : ATM_OC3_PCR;
 

drivers/atm/nicstar.c

@@ -153,7 +153,6 @@ static int ns_ioctl(struct atm_dev *dev, unsigned int cmd, void __user * arg);
 static void which_list(ns_dev * card, struct sk_buff *skb);
 #endif
 static void ns_poll(unsigned long arg);
-static int ns_parse_mac(char *mac, unsigned char *esi);
 static void ns_phy_put(struct atm_dev *dev, unsigned char value,
 		       unsigned long addr);
 static unsigned char ns_phy_get(struct atm_dev *dev, unsigned long addr);
@@ -779,7 +778,7 @@ static int ns_init_card(int i, struct pci_dev *pcidev)
 		return error;
 	}
 
-	if (ns_parse_mac(mac[i], card->atmdev->esi)) {
+	if (mac[i] == NULL || mac_pton(mac[i], card->atmdev->esi)) {
 		nicstar_read_eprom(card->membase, NICSTAR_EPROM_MAC_ADDR_OFFSET,
 				   card->atmdev->esi, 6);
 		if (memcmp(card->atmdev->esi, "\x00\x00\x00\x00\x00\x00", 6) ==
@@ -2802,29 +2801,6 @@ static void ns_poll(unsigned long arg)
 	PRINTK("nicstar: Leaving ns_poll().\n");
 }
 
-static int ns_parse_mac(char *mac, unsigned char *esi)
-{
-	int i, j;
-	short byte1, byte0;
-
-	if (mac == NULL || esi == NULL)
-		return -1;
-	j = 0;
-	for (i = 0; i < 6; i++) {
-		if ((byte1 = hex_to_bin(mac[j++])) < 0)
-			return -1;
-		if ((byte0 = hex_to_bin(mac[j++])) < 0)
-			return -1;
-		esi[i] = (unsigned char)(byte1 * 16 + byte0);
-		if (i < 5) {
-			if (mac[j++] != ':')
-				return -1;
-		}
-	}
-	return 0;
-}
-
-
 static void ns_phy_put(struct atm_dev *dev, unsigned char value,
 		       unsigned long addr)
 {

drivers/bcma/Kconfig

@@ -35,8 +35,14 @@ config BCMA_DRIVER_PCI_HOSTMODE
 	  PCI core hostmode operation (external PCI bus).
 
 config BCMA_HOST_SOC
-	bool
-	depends on BCMA_DRIVER_MIPS
+	bool "Support for BCMA in a SoC"
+	depends on BCMA
+	help
+	  Host interface for a Broadcom AIX bus directly mapped into
+	  the memory. This only works with the Broadcom SoCs from the
+	  BCM47XX line.
+
+	  If unsure, say N
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"

drivers/bcma/driver_pci.c

@@ -31,7 +31,7 @@ static void bcma_pcie_write(struct bcma_drv_pci *pc, u32 address, u32 data)
 	pcicore_write32(pc, BCMA_CORE_PCI_PCIEIND_DATA, data);
 }
 
-static void bcma_pcie_mdio_set_phy(struct bcma_drv_pci *pc, u8 phy)
+static void bcma_pcie_mdio_set_phy(struct bcma_drv_pci *pc, u16 phy)
 {
 	u32 v;
 	int i;
@@ -55,7 +55,7 @@ static void bcma_pcie_mdio_set_phy(struct bcma_drv_pci *pc, u8 phy)
 	}
 }
 
-static u16 bcma_pcie_mdio_read(struct bcma_drv_pci *pc, u8 device, u8 address)
+static u16 bcma_pcie_mdio_read(struct bcma_drv_pci *pc, u16 device, u8 address)
 {
 	int max_retries = 10;
 	u16 ret = 0;
@@ -98,7 +98,7 @@ static u16 bcma_pcie_mdio_read(struct bcma_drv_pci *pc, u8 device, u8 address)
 	return ret;
 }
 
-static void bcma_pcie_mdio_write(struct bcma_drv_pci *pc, u8 device,
+static void bcma_pcie_mdio_write(struct bcma_drv_pci *pc, u16 device,
 				u8 address, u16 data)
 {
 	int max_retries = 10;
@@ -137,6 +137,13 @@ static void bcma_pcie_mdio_write(struct bcma_drv_pci *pc, u8 device,
 	pcicore_write32(pc, BCMA_CORE_PCI_MDIO_CONTROL, 0);
 }
 
+static u16 bcma_pcie_mdio_writeread(struct bcma_drv_pci *pc, u16 device,
+				    u8 address, u16 data)
+{
+	bcma_pcie_mdio_write(pc, device, address, data);
+	return bcma_pcie_mdio_read(pc, device, address);
+}
+
 /**************************************************
  * Workarounds.
  **************************************************/
@@ -203,6 +210,25 @@ static void bcma_core_pci_config_fixup(struct bcma_drv_pci *pc)
 	}
 }
 
+static void bcma_core_pci_power_save(struct bcma_drv_pci *pc, bool up)
+{
+	u16 data;
+
+	if (pc->core->id.rev >= 15 && pc->core->id.rev <= 20) {
+		data = up ? 0x74 : 0x7C;
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT1, 0x7F64);
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT3, data);
+	} else if (pc->core->id.rev >= 21 && pc->core->id.rev <= 22) {
+		data = up ? 0x75 : 0x7D;
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT1, 0x7E65);
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT3, data);
+	}
+}
+
 /**************************************************
  * Init.
  **************************************************/
@@ -262,7 +288,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(bcma_core_pci_irq_ctl);
 
-void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend)
+static void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend)
 {
 	u32 w;
 
@@ -274,4 +300,33 @@ void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend)
 	bcma_pcie_write(pc, BCMA_CORE_PCI_DLLP_PMTHRESHREG, w);
 	bcma_pcie_read(pc, BCMA_CORE_PCI_DLLP_PMTHRESHREG);
 }
-EXPORT_SYMBOL_GPL(bcma_core_pci_extend_L1timer);
+
+void bcma_core_pci_up(struct bcma_bus *bus)
+{
+	struct bcma_drv_pci *pc;
+
+	if (bus->hosttype != BCMA_HOSTTYPE_PCI)
+		return;
+
+	pc = &bus->drv_pci[0];
+
+	bcma_core_pci_power_save(pc, true);
+
+	bcma_core_pci_extend_L1timer(pc, true);
+}
+EXPORT_SYMBOL_GPL(bcma_core_pci_up);
+
+void bcma_core_pci_down(struct bcma_bus *bus)
+{
+	struct bcma_drv_pci *pc;
+
+	if (bus->hosttype != BCMA_HOSTTYPE_PCI)
+		return;
+
+	pc = &bus->drv_pci[0];
+
+	bcma_core_pci_extend_L1timer(pc, false);
+
+	bcma_core_pci_power_save(pc, false);
+}
+EXPORT_SYMBOL_GPL(bcma_core_pci_down);

drivers/bcma/driver_pci_host.c

@@ -581,6 +581,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, bcma_core_pci_fixup_addresses);
 int bcma_core_pci_plat_dev_init(struct pci_dev *dev)
 {
 	struct bcma_drv_pci_host *pc_host;
+	int readrq;
 
 	if (dev->bus->ops->read != bcma_core_pci_hostmode_read_config) {
 		/* This is not a device on the PCI-core bridge. */
@@ -595,6 +596,11 @@ int bcma_core_pci_plat_dev_init(struct pci_dev *dev)
 	dev->irq = bcma_core_irq(pc_host->pdev->core);
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
 
+	readrq = pcie_get_readrq(dev);
+	if (readrq > 128) {
+		pr_info("change PCIe max read request size from %i to 128\n", readrq);
+		pcie_set_readrq(dev, 128);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(bcma_core_pci_plat_dev_init);

drivers/bcma/main.c

@@ -237,7 +237,7 @@ int bcma_bus_register(struct bcma_bus *bus)
 	err = bcma_bus_scan(bus);
 	if (err) {
 		bcma_err(bus, "Failed to scan: %d\n", err);
-		return -1;
+		return err;
 	}
 
 	/* Early init CC core */

drivers/bcma/scan.c

@@ -32,6 +32,18 @@ static const struct bcma_device_id_name bcma_bcm_device_names[] = {
 	{ BCMA_CORE_4706_CHIPCOMMON, "BCM4706 ChipCommon" },
 	{ BCMA_CORE_4706_SOC_RAM, "BCM4706 SOC RAM" },
 	{ BCMA_CORE_4706_MAC_GBIT, "BCM4706 GBit MAC" },
+	{ BCMA_CORE_PCIEG2, "PCIe Gen 2" },
+	{ BCMA_CORE_DMA, "DMA" },
+	{ BCMA_CORE_SDIO3, "SDIO3" },
+	{ BCMA_CORE_USB20, "USB 2.0" },
+	{ BCMA_CORE_USB30, "USB 3.0" },
+	{ BCMA_CORE_A9JTAG, "ARM Cortex A9 JTAG" },
+	{ BCMA_CORE_DDR23, "Denali DDR2/DDR3 memory controller" },
+	{ BCMA_CORE_ROM, "ROM" },
+	{ BCMA_CORE_NAND, "NAND flash controller" },
+	{ BCMA_CORE_QSPI, "SPI flash controller" },
+	{ BCMA_CORE_CHIPCOMMON_B, "Chipcommon B" },
+	{ BCMA_CORE_ARMCA9, "ARM Cortex A9 core (ihost)" },
 	{ BCMA_CORE_AMEMC, "AMEMC (DDR)" },
 	{ BCMA_CORE_ALTA, "ALTA (I2S)" },
 	{ BCMA_CORE_INVALID, "Invalid" },
@@ -201,7 +213,7 @@ static s32 bcma_erom_get_mst_port(struct bcma_bus *bus, u32 __iomem **eromptr)
 	return ent;
 }
 
-static s32 bcma_erom_get_addr_desc(struct bcma_bus *bus, u32 __iomem **eromptr,
+static u32 bcma_erom_get_addr_desc(struct bcma_bus *bus, u32 __iomem **eromptr,
 				  u32 type, u8 port)
 {
 	u32 addrl, addrh, sizel, sizeh = 0;
@@ -213,7 +225,7 @@ static s32 bcma_erom_get_addr_desc(struct bcma_bus *bus, u32 __iomem **eromptr,
 	    ((ent & SCAN_ADDR_TYPE) != type) ||
 	    (((ent & SCAN_ADDR_PORT) >> SCAN_ADDR_PORT_SHIFT) != port)) {
 		bcma_erom_push_ent(eromptr);
-		return -EINVAL;
+		return (u32)-EINVAL;
 	}
 
 	addrl = ent & SCAN_ADDR_ADDR;
@@ -261,7 +273,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 			      struct bcma_device_id *match, int core_num,
 			      struct bcma_device *core)
 {
-	s32 tmp;
+	u32 tmp;
 	u8 i, j;
 	s32 cia, cib;
 	u8 ports[2], wrappers[2];
@@ -339,11 +351,11 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 	 * the main register space for the core
 	 */
 	tmp = bcma_erom_get_addr_desc(bus, eromptr, SCAN_ADDR_TYPE_SLAVE, 0);
-	if (tmp <= 0) {
+	if (tmp == 0 || IS_ERR_VALUE(tmp)) {
 		/* Try again to see if it is a bridge */
 		tmp = bcma_erom_get_addr_desc(bus, eromptr,
 					      SCAN_ADDR_TYPE_BRIDGE, 0);
-		if (tmp <= 0) {
+		if (tmp == 0 || IS_ERR_VALUE(tmp)) {
 			return -EILSEQ;
 		} else {
 			bcma_info(bus, "Bridge found\n");
@@ -357,7 +369,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
 				SCAN_ADDR_TYPE_SLAVE, i);
-			if (tmp < 0) {
+			if (IS_ERR_VALUE(tmp)) {
 				/* no more entries for port _i_ */
 				/* pr_debug("erom: slave port %d "
 				 * "has %d descriptors\n", i, j); */
@@ -374,7 +386,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
 				SCAN_ADDR_TYPE_MWRAP, i);
-			if (tmp < 0) {
+			if (IS_ERR_VALUE(tmp)) {
 				/* no more entries for port _i_ */
 				/* pr_debug("erom: master wrapper %d "
 				 * "has %d descriptors\n", i, j); */
@@ -392,7 +404,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
 				SCAN_ADDR_TYPE_SWRAP, i + hack);
-			if (tmp < 0) {
+			if (IS_ERR_VALUE(tmp)) {
 				/* no more entries for port _i_ */
 				/* pr_debug("erom: master wrapper %d "
 				 * has %d descriptors\n", i, j); */

drivers/bluetooth/btmrvl_debugfs.c

@@ -43,7 +43,7 @@ static ssize_t btmrvl_hscfgcmd_write(struct file *file,
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
 
-	ret = strict_strtol(buf, 10, &result);
+	ret = kstrtol(buf, 10, &result);
 	if (ret)
 		return ret;
 
@@ -89,7 +89,7 @@ static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf,
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
 
-	ret = strict_strtol(buf, 10, &result);
+	ret = kstrtol(buf, 10, &result);
 	if (ret)
 		return ret;
 
@@ -135,7 +135,7 @@ static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf,
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
 
-	ret = strict_strtol(buf, 10, &result);
+	ret = kstrtol(buf, 10, &result);
 	if (ret)
 		return ret;
 

drivers/bluetooth/btmrvl_sdio.c

@@ -486,7 +486,7 @@ static int btmrvl_sdio_download_fw_w_helper(struct btmrvl_sdio_card *card)
 			if (firmwarelen - offset < txlen)
 				txlen = firmwarelen - offset;
 
-			tx_blocks = (txlen + blksz_dl - 1) / blksz_dl;
+			tx_blocks = DIV_ROUND_UP(txlen, blksz_dl);
 
 			memcpy(fwbuf, &firmware[offset], txlen);
 		}
@@ -873,7 +873,7 @@ static int btmrvl_sdio_host_to_card(struct btmrvl_private *priv,
 	}
 
 	blksz = SDIO_BLOCK_SIZE;
-	buf_block_len = (nb + blksz - 1) / blksz;
+	buf_block_len = DIV_ROUND_UP(nb, blksz);
 
 	sdio_claim_host(card->func);
 

drivers/isdn/hardware/mISDN/hfcpci.c

@@ -1307,11 +1307,11 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
 		}
 		if (fifo2 & 2) {
 			hc->hw.fifo_en &= ~HFCPCI_FIFOEN_B2;
-			hc->hw.int_m1 &= ~(HFCPCI_INTS_B2TRANS +
+			hc->hw.int_m1 &= ~(HFCPCI_INTS_B2TRANS |
 					   HFCPCI_INTS_B2REC);
 		} else {
 			hc->hw.fifo_en &= ~HFCPCI_FIFOEN_B1;
-			hc->hw.int_m1 &= ~(HFCPCI_INTS_B1TRANS +
+			hc->hw.int_m1 &= ~(HFCPCI_INTS_B1TRANS |
 					   HFCPCI_INTS_B1REC);
 		}
 #ifdef REVERSE_BITORDER
@@ -1346,14 +1346,14 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
 		if (fifo2 & 2) {
 			hc->hw.fifo_en |= HFCPCI_FIFOEN_B2;
 			if (!tics)
-				hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS +
+				hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS |
 						  HFCPCI_INTS_B2REC);
 			hc->hw.ctmt |= 2;
 			hc->hw.conn &= ~0x18;
 		} else {
 			hc->hw.fifo_en |= HFCPCI_FIFOEN_B1;
 			if (!tics)
-				hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS +
+				hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS |
 						  HFCPCI_INTS_B1REC);
 			hc->hw.ctmt |= 1;
 			hc->hw.conn &= ~0x03;
@@ -1375,14 +1375,14 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
 		if (fifo2 & 2) {
 			hc->hw.last_bfifo_cnt[1] = 0;
 			hc->hw.fifo_en |= HFCPCI_FIFOEN_B2;
-			hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS +
+			hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS |
 					  HFCPCI_INTS_B2REC);
 			hc->hw.ctmt &= ~2;
 			hc->hw.conn &= ~0x18;
 		} else {
 			hc->hw.last_bfifo_cnt[0] = 0;
 			hc->hw.fifo_en |= HFCPCI_FIFOEN_B1;
-			hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS +
+			hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS |
 					  HFCPCI_INTS_B1REC);
 			hc->hw.ctmt &= ~1;
 			hc->hw.conn &= ~0x03;

drivers/net/bonding/bond_3ad.c

@@ -143,10 +143,9 @@ static inline struct bonding *__get_bond_by_port(struct port *port)
  */
 static inline struct port *__get_first_port(struct bonding *bond)
 {
-	if (bond->slave_cnt == 0)
-		return NULL;
+	struct slave *first_slave = bond_first_slave(bond);
 
-	return &(SLAVE_AD_INFO(bond->first_slave).port);
+	return first_slave ? &(SLAVE_AD_INFO(first_slave).port) : NULL;
 }
 
 /**
@@ -159,13 +158,16 @@ static inline struct port *__get_first_port(struct bonding *bond)
 static inline struct port *__get_next_port(struct port *port)
 {
 	struct bonding *bond = __get_bond_by_port(port);
-	struct slave *slave = port->slave;
+	struct slave *slave = port->slave, *slave_next;
 
 	// If there's no bond for this port, or this is the last slave
-	if ((bond == NULL) || (slave->next == bond->first_slave))
+	if (bond == NULL)
+		return NULL;
+	slave_next = bond_next_slave(bond, slave);
+	if (!slave_next || bond_is_first_slave(bond, slave_next))
 		return NULL;
 
-	return &(SLAVE_AD_INFO(slave->next).port);
+	return &(SLAVE_AD_INFO(slave_next).port);
 }
 
 /**
@@ -178,12 +180,14 @@ static inline struct port *__get_next_port(struct port *port)
 static inline struct aggregator *__get_first_agg(struct port *port)
 {
 	struct bonding *bond = __get_bond_by_port(port);
+	struct slave *first_slave;
 
 	// If there's no bond for this port, or bond has no slaves
-	if ((bond == NULL) || (bond->slave_cnt == 0))
+	if (bond == NULL)
 		return NULL;
+	first_slave = bond_first_slave(bond);
 
-	return &(SLAVE_AD_INFO(bond->first_slave).aggregator);
+	return first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL;
 }
 
 /**
@@ -195,14 +199,17 @@ static inline struct aggregator *__get_first_agg(struct port *port)
  */
 static inline struct aggregator *__get_next_agg(struct aggregator *aggregator)
 {
-	struct slave *slave = aggregator->slave;
+	struct slave *slave = aggregator->slave, *slave_next;
 	struct bonding *bond = bond_get_bond_by_slave(slave);
 
 	// If there's no bond for this aggregator, or this is the last slave
-	if ((bond == NULL) || (slave->next == bond->first_slave))
+	if (bond == NULL)
+		return NULL;
+	slave_next = bond_next_slave(bond, slave);
+	if (!slave_next || bond_is_first_slave(bond, slave_next))
 		return NULL;
 
-	return &(SLAVE_AD_INFO(slave->next).aggregator);
+	return &(SLAVE_AD_INFO(slave_next).aggregator);
 }
 
 /*
@@ -2110,7 +2117,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	read_lock(&bond->lock);
 
 	//check if there are any slaves
-	if (bond->slave_cnt == 0)
+	if (list_empty(&bond->slave_list))
 		goto re_arm;
 
 	// check if agg_select_timer timer after initialize is timed out
@@ -2336,8 +2343,12 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 int bond_3ad_set_carrier(struct bonding *bond)
 {
 	struct aggregator *active;
+	struct slave *first_slave;
 
-	active = __get_active_agg(&(SLAVE_AD_INFO(bond->first_slave).aggregator));
+	first_slave = bond_first_slave(bond);
+	if (!first_slave)
+		return 0;
+	active = __get_active_agg(&(SLAVE_AD_INFO(first_slave).aggregator));
 	if (active) {
 		/* are enough slaves available to consider link up? */
 		if (active->num_of_ports < bond->params.min_links) {
@@ -2415,6 +2426,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 	struct ad_info ad_info;
 	int res = 1;
 
+	read_lock(&bond->lock);
 	if (__bond_3ad_get_active_agg_info(bond, &ad_info)) {
 		pr_debug("%s: Error: __bond_3ad_get_active_agg_info failed\n",
 			 dev->name);
@@ -2432,7 +2444,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 
 	slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg);
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator;
 
 		if (agg && (agg->aggregator_identifier == agg_id)) {
@@ -2464,6 +2476,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 	}
 
 out:
+	read_unlock(&bond->lock);
 	if (res) {
 		/* no suitable interface, frame not sent */
 		kfree_skb(skb);
@@ -2501,18 +2514,13 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
  */
 void bond_3ad_update_lacp_rate(struct bonding *bond)
 {
-	int i;
-	struct slave *slave;
 	struct port *port = NULL;
+	struct slave *slave;
 	int lacp_fast;
 
-	write_lock_bh(&bond->lock);
 	lacp_fast = bond->params.lacp_fast;
-
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		port = &(SLAVE_AD_INFO(slave).port);
-		if (port->slave == NULL)
-			continue;
 		__get_state_machine_lock(port);
 		if (lacp_fast)
 			port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT;
@@ -2520,6 +2528,4 @@ void bond_3ad_update_lacp_rate(struct bonding *bond)
 			port->actor_oper_port_state &= ~AD_STATE_LACP_TIMEOUT;
 		__release_state_machine_lock(port);
 	}
-
-	write_unlock_bh(&bond->lock);
 }

drivers/net/bonding/bond_alb.c

@@ -224,13 +224,12 @@ static struct slave *tlb_get_least_loaded_slave(struct bonding *bond)
 {
 	struct slave *slave, *least_loaded;
 	long long max_gap;
-	int i;
 
 	least_loaded = NULL;
 	max_gap = LLONG_MIN;
 
 	/* Find the slave with the largest gap */
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (SLAVE_IS_OK(slave)) {
 			long long gap = compute_gap(slave);
 
@@ -386,11 +385,10 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond)
 	struct slave *rx_slave, *slave, *start_at;
 	int i = 0;
 
-	if (bond_info->next_rx_slave) {
+	if (bond_info->next_rx_slave)
 		start_at = bond_info->next_rx_slave;
-	} else {
-		start_at = bond->first_slave;
-	}
+	else
+		start_at = bond_first_slave(bond);
 
 	rx_slave = NULL;
 
@@ -405,7 +403,8 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond)
 	}
 
 	if (rx_slave) {
-		bond_info->next_rx_slave = rx_slave->next;
+		slave = bond_next_slave(bond, rx_slave);
+		bond_info->next_rx_slave = slave;
 	}
 
 	return rx_slave;
@@ -513,7 +512,7 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 
 		skb->dev = client_info->slave->dev;
 
-		if (client_info->tag) {
+		if (client_info->vlan_id) {
 			skb = vlan_put_tag(skb, htons(ETH_P_8021Q), client_info->vlan_id);
 			if (!skb) {
 				pr_err("%s: Error: failed to insert VLAN tag\n",
@@ -695,10 +694,8 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon
 			client_info->ntt = 0;
 		}
 
-		if (bond_vlan_used(bond)) {
-			if (!vlan_get_tag(skb, &client_info->vlan_id))
-				client_info->tag = 1;
-		}
+		if (!vlan_get_tag(skb, &client_info->vlan_id))
+			client_info->vlan_id = 0;
 
 		if (!client_info->assigned) {
 			u32 prev_tbl_head = bond_info->rx_hashtbl_used_head;
@@ -804,7 +801,7 @@ static void rlb_init_table_entry_dst(struct rlb_client_info *entry)
 	entry->used_prev = RLB_NULL_INDEX;
 	entry->assigned = 0;
 	entry->slave = NULL;
-	entry->tag = 0;
+	entry->vlan_id = 0;
 }
 static void rlb_init_table_entry_src(struct rlb_client_info *entry)
 {
@@ -961,7 +958,7 @@ static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id)
 		struct rlb_client_info *curr = &(bond_info->rx_hashtbl[curr_index]);
 		u32 next_index = bond_info->rx_hashtbl[curr_index].used_next;
 
-		if (curr->tag && (curr->vlan_id == vlan_id))
+		if (curr->vlan_id == vlan_id)
 			rlb_delete_table_entry(bond, curr_index);
 
 		curr_index = next_index;
@@ -972,58 +969,62 @@ static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id)
 
 /*********************** tlb/rlb shared functions *********************/
 
-static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[])
+static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
+			    u16 vid)
 {
-	struct bonding *bond = bond_get_bond_by_slave(slave);
 	struct learning_pkt pkt;
+	struct sk_buff *skb;
 	int size = sizeof(struct learning_pkt);
-	int i;
+	char *data;
 
 	memset(&pkt, 0, size);
 	memcpy(pkt.mac_dst, mac_addr, ETH_ALEN);
 	memcpy(pkt.mac_src, mac_addr, ETH_ALEN);
 	pkt.type = cpu_to_be16(ETH_P_LOOP);
 
-	for (i = 0; i < MAX_LP_BURST; i++) {
-		struct sk_buff *skb;
-		char *data;
+	skb = dev_alloc_skb(size);
+	if (!skb)
+		return;
+
+	data = skb_put(skb, size);
+	memcpy(data, &pkt, size);
+
+	skb_reset_mac_header(skb);
+	skb->network_header = skb->mac_header + ETH_HLEN;
+	skb->protocol = pkt.type;
+	skb->priority = TC_PRIO_CONTROL;
+	skb->dev = slave->dev;
 
-		skb = dev_alloc_skb(size);
+	if (vid) {
+		skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vid);
 		if (!skb) {
+			pr_err("%s: Error: failed to insert VLAN tag\n",
+			       slave->bond->dev->name);
 			return;
 		}
+	}
 
-		data = skb_put(skb, size);
-		memcpy(data, &pkt, size);
-
-		skb_reset_mac_header(skb);
-		skb->network_header = skb->mac_header + ETH_HLEN;
-		skb->protocol = pkt.type;
-		skb->priority = TC_PRIO_CONTROL;
-		skb->dev = slave->dev;
+	dev_queue_xmit(skb);
+}
 
-		if (bond_vlan_used(bond)) {
-			struct vlan_entry *vlan;
 
-			vlan = bond_next_vlan(bond,
-					      bond->alb_info.current_alb_vlan);
+static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[])
+{
+	struct bonding *bond = bond_get_bond_by_slave(slave);
+	struct net_device *upper;
+	struct list_head *iter;
 
-			bond->alb_info.current_alb_vlan = vlan;
-			if (!vlan) {
-				kfree_skb(skb);
-				continue;
-			}
+	/* send untagged */
+	alb_send_lp_vid(slave, mac_addr, 0);
 
-			skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vlan->vlan_id);
-			if (!skb) {
-				pr_err("%s: Error: failed to insert VLAN tag\n",
-				       bond->dev->name);
-				continue;
-			}
-		}
-
-		dev_queue_xmit(skb);
+	/* loop through vlans and send one packet for each */
+	rcu_read_lock();
+	netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+		if (upper->priv_flags & IFF_802_1Q_VLAN)
+			alb_send_lp_vid(slave, mac_addr,
+					vlan_dev_vlan_id(upper));
 	}
+	rcu_read_unlock();
 }
 
 static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
@@ -1173,9 +1174,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 {
 	struct slave *tmp_slave1, *free_mac_slave = NULL;
 	struct slave *has_bond_addr = bond->curr_active_slave;
-	int i;
 
-	if (bond->slave_cnt == 0) {
+	if (list_empty(&bond->slave_list)) {
 		/* this is the first slave */
 		return 0;
 	}
@@ -1196,7 +1196,7 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 	/* The slave's address is equal to the address of the bond.
 	 * Search for a spare address in the bond for this slave.
 	 */
-	bond_for_each_slave(bond, tmp_slave1, i) {
+	bond_for_each_slave(bond, tmp_slave1) {
 		if (!bond_slave_has_mac(bond, tmp_slave1->perm_hwaddr)) {
 			/* no slave has tmp_slave1's perm addr
 			 * as its curr addr
@@ -1246,17 +1246,15 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
  */
 static int alb_set_mac_address(struct bonding *bond, void *addr)
 {
-	struct sockaddr sa;
-	struct slave *slave, *stop_at;
 	char tmp_addr[ETH_ALEN];
+	struct slave *slave;
+	struct sockaddr sa;
 	int res;
-	int i;
 
-	if (bond->alb_info.rlb_enabled) {
+	if (bond->alb_info.rlb_enabled)
 		return 0;
-	}
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		/* save net_device's current hw address */
 		memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN);
 
@@ -1276,8 +1274,7 @@ unwind:
 	sa.sa_family = bond->dev->type;
 
 	/* unwind from head to the slave that failed */
-	stop_at = slave;
-	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) {
+	bond_for_each_slave_continue_reverse(bond, slave) {
 		memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN);
 		dev_set_mac_address(slave->dev, &sa);
 		memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN);
@@ -1342,6 +1339,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 
 	/* make sure that the curr_active_slave do not change during tx
 	 */
+	read_lock(&bond->lock);
 	read_lock(&bond->curr_slave_lock);
 
 	switch (ntohs(skb->protocol)) {
@@ -1446,11 +1444,12 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	}
 
 	read_unlock(&bond->curr_slave_lock);
-
+	read_unlock(&bond->lock);
 	if (res) {
 		/* no suitable interface, frame not sent */
 		kfree_skb(skb);
 	}
+
 	return NETDEV_TX_OK;
 }
 
@@ -1460,11 +1459,10 @@ void bond_alb_monitor(struct work_struct *work)
 					    alb_work.work);
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
 	struct slave *slave;
-	int i;
 
 	read_lock(&bond->lock);
 
-	if (bond->slave_cnt == 0) {
+	if (list_empty(&bond->slave_list)) {
 		bond_info->tx_rebalance_counter = 0;
 		bond_info->lp_counter = 0;
 		goto re_arm;
@@ -1482,9 +1480,8 @@ void bond_alb_monitor(struct work_struct *work)
 		 */
 		read_lock(&bond->curr_slave_lock);
 
-		bond_for_each_slave(bond, slave, i) {
+		bond_for_each_slave(bond, slave)
 			alb_send_learning_packets(slave, slave->dev->dev_addr);
-		}
 
 		read_unlock(&bond->curr_slave_lock);
 
@@ -1496,7 +1493,7 @@ void bond_alb_monitor(struct work_struct *work)
 
 		read_lock(&bond->curr_slave_lock);
 
-		bond_for_each_slave(bond, slave, i) {
+		bond_for_each_slave(bond, slave) {
 			tlb_clear_slave(bond, slave, 1);
 			if (slave == bond->curr_active_slave) {
 				SLAVE_TLB_INFO(slave).load =
@@ -1602,9 +1599,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave)
  */
 void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave)
 {
-	if (bond->slave_cnt > 1) {
+	if (!list_empty(&bond->slave_list))
 		alb_change_hw_addr_on_detach(bond, slave);
-	}
 
 	tlb_clear_slave(bond, slave, 0);
 
@@ -1661,9 +1657,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 {
 	struct slave *swap_slave;
 
-	if (bond->curr_active_slave == new_slave) {
+	if (bond->curr_active_slave == new_slave)
 		return;
-	}
 
 	if (bond->curr_active_slave && bond->alb_info.primary_is_promisc) {
 		dev_set_promiscuity(bond->curr_active_slave->dev, -1);
@@ -1672,11 +1667,10 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	}
 
 	swap_slave = bond->curr_active_slave;
-	bond->curr_active_slave = new_slave;
+	rcu_assign_pointer(bond->curr_active_slave, new_slave);
 
-	if (!new_slave || (bond->slave_cnt == 0)) {
+	if (!new_slave || list_empty(&bond->slave_list))
 		return;
-	}
 
 	/* set the new curr_active_slave to the bonds mac address
 	 * i.e. swap mac addresses of old curr_active_slave and new curr_active_slave
@@ -1689,9 +1683,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	 * ignored so we can mess with their MAC addresses without
 	 * fear of interference from transmit activity.
 	 */
-	if (swap_slave) {
+	if (swap_slave)
 		tlb_clear_slave(bond, swap_slave, 1);
-	}
 	tlb_clear_slave(bond, new_slave, 1);
 
 	write_unlock_bh(&bond->curr_slave_lock);
@@ -1768,11 +1761,6 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 
 void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id)
 {
-	if (bond->alb_info.current_alb_vlan &&
-	    (bond->alb_info.current_alb_vlan->vlan_id == vlan_id)) {
-		bond->alb_info.current_alb_vlan = NULL;
-	}
-
 	if (bond->alb_info.rlb_enabled) {
 		rlb_clear_vlan(bond, vlan_id);
 	}

drivers/net/bonding/bond_alb.h

@@ -53,7 +53,6 @@ struct slave;
 
 
 #define TLB_NULL_INDEX		0xffffffff
-#define MAX_LP_BURST		3
 
 /* rlb defs */
 #define RLB_HASH_TABLE_SIZE	256
@@ -126,7 +125,6 @@ struct rlb_client_info {
 	u8  assigned;		/* checking whether this entry is assigned */
 	u8  ntt;		/* flag - need to transmit client info */
 	struct slave *slave;	/* the slave assigned to this client */
-	u8 tag;			/* flag - need to tag skb */
 	unsigned short vlan_id;	/* VLAN tag associated with IP address */
 };
 
@@ -170,7 +168,6 @@ struct alb_bond_info {
 						 * rx traffic should be
 						 * rebalanced
 						 */
-	struct vlan_entry	*current_alb_vlan;
 };
 
 int bond_alb_initialize(struct bonding *bond, int rlb_enabled);

drivers/net/bonding/bond_main.c

@@ -77,6 +77,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/pkt_sched.h>
+#include <linux/rculist.h>
 #include "bonding.h"
 #include "bond_3ad.h"
 #include "bond_alb.h"
@@ -106,7 +107,7 @@ static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
 static char *arp_validate;
 static char *arp_all_targets;
 static char *fail_over_mac;
-static int all_slaves_active = 0;
+static int all_slaves_active;
 static struct bond_params bonding_defaults;
 static int resend_igmp = BOND_DEFAULT_RESEND_IGMP;
 
@@ -273,7 +274,7 @@ const char *bond_mode_name(int mode)
 		[BOND_MODE_ALB] = "adaptive load balancing",
 	};
 
-	if (mode < 0 || mode > BOND_MODE_ALB)
+	if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB)
 		return "unknown";
 
 	return names[mode];
@@ -281,116 +282,6 @@ const char *bond_mode_name(int mode)
 
 /*---------------------------------- VLAN -----------------------------------*/
 
-/**
- * bond_add_vlan - add a new vlan id on bond
- * @bond: bond that got the notification
- * @vlan_id: the vlan id to add
- *
- * Returns -ENOMEM if allocation failed.
- */
-static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id)
-{
-	struct vlan_entry *vlan;
-
-	pr_debug("bond: %s, vlan id %d\n",
-		 (bond ? bond->dev->name : "None"), vlan_id);
-
-	vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL);
-	if (!vlan)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&vlan->vlan_list);
-	vlan->vlan_id = vlan_id;
-
-	write_lock_bh(&bond->lock);
-
-	list_add_tail(&vlan->vlan_list, &bond->vlan_list);
-
-	write_unlock_bh(&bond->lock);
-
-	pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name);
-
-	return 0;
-}
-
-/**
- * bond_del_vlan - delete a vlan id from bond
- * @bond: bond that got the notification
- * @vlan_id: the vlan id to delete
- *
- * returns -ENODEV if @vlan_id was not found in @bond.
- */
-static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id)
-{
-	struct vlan_entry *vlan;
-	int res = -ENODEV;
-
-	pr_debug("bond: %s, vlan id %d\n", bond->dev->name, vlan_id);
-
-	block_netpoll_tx();
-	write_lock_bh(&bond->lock);
-
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		if (vlan->vlan_id == vlan_id) {
-			list_del(&vlan->vlan_list);
-
-			if (bond_is_lb(bond))
-				bond_alb_clear_vlan(bond, vlan_id);
-
-			pr_debug("removed VLAN ID %d from bond %s\n",
-				 vlan_id, bond->dev->name);
-
-			kfree(vlan);
-
-			res = 0;
-			goto out;
-		}
-	}
-
-	pr_debug("couldn't find VLAN ID %d in bond %s\n",
-		 vlan_id, bond->dev->name);
-
-out:
-	write_unlock_bh(&bond->lock);
-	unblock_netpoll_tx();
-	return res;
-}
-
-/**
- * bond_next_vlan - safely skip to the next item in the vlans list.
- * @bond: the bond we're working on
- * @curr: item we're advancing from
- *
- * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL,
- * or @curr->next otherwise (even if it is @curr itself again).
- *
- * Caller must hold bond->lock
- */
-struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr)
-{
-	struct vlan_entry *next, *last;
-
-	if (list_empty(&bond->vlan_list))
-		return NULL;
-
-	if (!curr) {
-		next = list_entry(bond->vlan_list.next,
-				  struct vlan_entry, vlan_list);
-	} else {
-		last = list_entry(bond->vlan_list.prev,
-				  struct vlan_entry, vlan_list);
-		if (last == curr) {
-			next = list_entry(bond->vlan_list.next,
-					  struct vlan_entry, vlan_list);
-		} else {
-			next = list_entry(curr->vlan_list.next,
-					  struct vlan_entry, vlan_list);
-		}
-	}
-
-	return next;
-}
-
 /**
  * bond_dev_queue_xmit - Prepare skb for xmit.
  *
@@ -441,28 +332,20 @@ static int bond_vlan_rx_add_vid(struct net_device *bond_dev,
 				__be16 proto, u16 vid)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave, *stop_at;
-	int i, res;
+	struct slave *slave;
+	int res;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		res = vlan_vid_add(slave->dev, proto, vid);
 		if (res)
 			goto unwind;
 	}
 
-	res = bond_add_vlan(bond, vid);
-	if (res) {
-		pr_err("%s: Error: Failed to add vlan id %d\n",
-		       bond_dev->name, vid);
-		return res;
-	}
-
 	return 0;
 
 unwind:
-	/* unwind from head to the slave that failed */
-	stop_at = slave;
-	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at)
+	/* unwind from the slave that failed */
+	bond_for_each_slave_continue_reverse(bond, slave)
 		vlan_vid_del(slave->dev, proto, vid);
 
 	return res;
@@ -478,48 +361,16 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
-	int i, res;
 
-	bond_for_each_slave(bond, slave, i)
+	bond_for_each_slave(bond, slave)
 		vlan_vid_del(slave->dev, proto, vid);
 
-	res = bond_del_vlan(bond, vid);
-	if (res) {
-		pr_err("%s: Error: Failed to remove vlan id %d\n",
-		       bond_dev->name, vid);
-		return res;
-	}
+	if (bond_is_lb(bond))
+		bond_alb_clear_vlan(bond, vid);
 
 	return 0;
 }
 
-static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev)
-{
-	struct vlan_entry *vlan;
-	int res;
-
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		res = vlan_vid_add(slave_dev, htons(ETH_P_8021Q),
-				   vlan->vlan_id);
-		if (res)
-			pr_warning("%s: Failed to add vlan id %d to device %s\n",
-				   bond->dev->name, vlan->vlan_id,
-				   slave_dev->name);
-	}
-}
-
-static void bond_del_vlans_from_slave(struct bonding *bond,
-				      struct net_device *slave_dev)
-{
-	struct vlan_entry *vlan;
-
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		if (!vlan->vlan_id)
-			continue;
-		vlan_vid_del(slave_dev, htons(ETH_P_8021Q), vlan->vlan_id);
-	}
-}
-
 /*------------------------------- Link status -------------------------------*/
 
 /*
@@ -532,15 +383,14 @@ static void bond_del_vlans_from_slave(struct bonding *bond,
 static int bond_set_carrier(struct bonding *bond)
 {
 	struct slave *slave;
-	int i;
 
-	if (bond->slave_cnt == 0)
+	if (list_empty(&bond->slave_list))
 		goto down;
 
 	if (bond->params.mode == BOND_MODE_8023AD)
 		return bond_3ad_set_carrier(bond);
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (slave->link == BOND_LINK_UP) {
 			if (!netif_carrier_ok(bond->dev)) {
 				netif_carrier_on(bond->dev);
@@ -681,8 +531,8 @@ static int bond_set_promiscuity(struct bonding *bond, int inc)
 		}
 	} else {
 		struct slave *slave;
-		int i;
-		bond_for_each_slave(bond, slave, i) {
+
+		bond_for_each_slave(bond, slave) {
 			err = dev_set_promiscuity(slave->dev, inc);
 			if (err)
 				return err;
@@ -705,8 +555,8 @@ static int bond_set_allmulti(struct bonding *bond, int inc)
 		}
 	} else {
 		struct slave *slave;
-		int i;
-		bond_for_each_slave(bond, slave, i) {
+
+		bond_for_each_slave(bond, slave) {
 			err = dev_set_allmulti(slave->dev, inc);
 			if (err)
 				return err;
@@ -715,15 +565,6 @@ static int bond_set_allmulti(struct bonding *bond, int inc)
 	return err;
 }
 
-static void __bond_resend_igmp_join_requests(struct net_device *dev)
-{
-	struct in_device *in_dev;
-
-	in_dev = __in_dev_get_rcu(dev);
-	if (in_dev)
-		ip_mc_rejoin_groups(in_dev);
-}
-
 /*
  * Retrieve the list of registered multicast addresses for the bonding
  * device and retransmit an IGMP JOIN request to the current active
@@ -731,33 +572,12 @@ static void __bond_resend_igmp_join_requests(struct net_device *dev)
  */
 static void bond_resend_igmp_join_requests(struct bonding *bond)
 {
-	struct net_device *bond_dev, *vlan_dev, *upper_dev;
-	struct vlan_entry *vlan;
-
-	read_lock(&bond->lock);
-	rcu_read_lock();
-
-	bond_dev = bond->dev;
-
-	/* rejoin all groups on bond device */
-	__bond_resend_igmp_join_requests(bond_dev);
-
-	/*
-	 * if bond is enslaved to a bridge,
-	 * then rejoin all groups on its master
-	 */
-	upper_dev = netdev_master_upper_dev_get_rcu(bond_dev);
-	if (upper_dev && upper_dev->priv_flags & IFF_EBRIDGE)
-		__bond_resend_igmp_join_requests(upper_dev);
-
-	/* rejoin all groups on vlan devices */
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		vlan_dev = __vlan_find_dev_deep(bond_dev, htons(ETH_P_8021Q),
-						vlan->vlan_id);
-		if (vlan_dev)
-			__bond_resend_igmp_join_requests(vlan_dev);
+	if (!rtnl_trylock()) {
+		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
+		return;
 	}
-	rcu_read_unlock();
+	call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev);
+	rtnl_unlock();
 
 	/* We use curr_slave_lock to protect against concurrent access to
 	 * igmp_retrans from multiple running instances of this function and
@@ -769,7 +589,6 @@ static void bond_resend_igmp_join_requests(struct bonding *bond)
 		queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
 	}
 	write_unlock_bh(&bond->curr_slave_lock);
-	read_unlock(&bond->lock);
 }
 
 static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
@@ -808,6 +627,8 @@ static void bond_hw_addr_flush(struct net_device *bond_dev,
 static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 			      struct slave *old_active)
 {
+	ASSERT_RTNL();
+
 	if (old_active) {
 		if (bond->dev->flags & IFF_PROMISC)
 			dev_set_promiscuity(old_active->dev, -1);
@@ -966,9 +787,8 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 	new_active = bond->curr_active_slave;
 
 	if (!new_active) { /* there were no active slaves left */
-		if (bond->slave_cnt > 0)   /* found one slave */
-			new_active = bond->first_slave;
-		else
+		new_active = bond_first_slave(bond);
+		if (!new_active)
 			return NULL; /* still no slave, return NULL */
 	}
 
@@ -1008,7 +828,6 @@ static bool bond_should_notify_peers(struct bonding *bond)
 	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
 		return false;
 
-	bond->send_peer_notif--;
 	return true;
 }
 
@@ -1071,7 +890,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 		if (new_active)
 			bond_set_slave_active_flags(new_active);
 	} else {
-		bond->curr_active_slave = new_active;
+		rcu_assign_pointer(bond->curr_active_slave, new_active);
 	}
 
 	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
@@ -1115,7 +934,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 	    ((USES_PRIMARY(bond->params.mode) && new_active) ||
 	     bond->params.mode == BOND_MODE_ROUNDROBIN)) {
 		bond->igmp_retrans = bond->params.resend_igmp;
-		queue_delayed_work(bond->wq, &bond->mcast_work, 0);
+		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
 	}
 }
 
@@ -1161,17 +980,7 @@ void bond_select_active_slave(struct bonding *bond)
  */
 static void bond_attach_slave(struct bonding *bond, struct slave *new_slave)
 {
-	if (bond->first_slave == NULL) { /* attaching the first slave */
-		new_slave->next = new_slave;
-		new_slave->prev = new_slave;
-		bond->first_slave = new_slave;
-	} else {
-		new_slave->next = bond->first_slave;
-		new_slave->prev = bond->first_slave->prev;
-		new_slave->next->prev = new_slave;
-		new_slave->prev->next = new_slave;
-	}
-
+	list_add_tail_rcu(&new_slave->list, &bond->slave_list);
 	bond->slave_cnt++;
 }
 
@@ -1187,22 +996,7 @@ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave)
  */
 static void bond_detach_slave(struct bonding *bond, struct slave *slave)
 {
-	if (slave->next)
-		slave->next->prev = slave->prev;
-
-	if (slave->prev)
-		slave->prev->next = slave->next;
-
-	if (bond->first_slave == slave) { /* slave is the first slave */
-		if (bond->slave_cnt > 1) { /* there are more slave */
-			bond->first_slave = slave->next;
-		} else {
-			bond->first_slave = NULL; /* slave was the last one */
-		}
-	}
-
-	slave->next = NULL;
-	slave->prev = NULL;
+	list_del_rcu(&slave->list);
 	bond->slave_cnt--;
 }
 
@@ -1249,47 +1043,31 @@ static void bond_poll_controller(struct net_device *bond_dev)
 {
 }
 
-static void __bond_netpoll_cleanup(struct bonding *bond)
+static void bond_netpoll_cleanup(struct net_device *bond_dev)
 {
+	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
-	int i;
 
-	bond_for_each_slave(bond, slave, i)
+	bond_for_each_slave(bond, slave)
 		if (IS_UP(slave->dev))
 			slave_disable_netpoll(slave);
 }
-static void bond_netpoll_cleanup(struct net_device *bond_dev)
-{
-	struct bonding *bond = netdev_priv(bond_dev);
-
-	read_lock(&bond->lock);
-	__bond_netpoll_cleanup(bond);
-	read_unlock(&bond->lock);
-}
 
 static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp)
 {
 	struct bonding *bond = netdev_priv(dev);
 	struct slave *slave;
-	int i, err = 0;
+	int err = 0;
 
-	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		err = slave_enable_netpoll(slave);
 		if (err) {
-			__bond_netpoll_cleanup(bond);
+			bond_netpoll_cleanup(dev);
 			break;
 		}
 	}
-	read_unlock(&bond->lock);
 	return err;
 }
-
-static struct netpoll_info *bond_netpoll_info(struct bonding *bond)
-{
-	return bond->dev->npinfo;
-}
-
 #else
 static inline int slave_enable_netpoll(struct slave *slave)
 {
@@ -1306,34 +1084,29 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
 /*---------------------------------- IOCTL ----------------------------------*/
 
 static netdev_features_t bond_fix_features(struct net_device *dev,
-	netdev_features_t features)
+					   netdev_features_t features)
 {
-	struct slave *slave;
 	struct bonding *bond = netdev_priv(dev);
 	netdev_features_t mask;
-	int i;
-
-	read_lock(&bond->lock);
+	struct slave *slave;
 
-	if (!bond->first_slave) {
+	if (list_empty(&bond->slave_list)) {
 		/* Disable adding VLANs to empty bond. But why? --mq */
 		features |= NETIF_F_VLAN_CHALLENGED;
-		goto out;
+		return features;
 	}
 
 	mask = features;
 	features &= ~NETIF_F_ONE_FOR_ALL;
 	features |= NETIF_F_ALL_FOR_ALL;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		features = netdev_increment_features(features,
 						     slave->dev->features,
 						     mask);
 	}
 	features = netdev_add_tso_features(features, mask);
 
-out:
-	read_unlock(&bond->lock);
 	return features;
 }
 
@@ -1343,21 +1116,18 @@ out:
 
 static void bond_compute_features(struct bonding *bond)
 {
-	struct slave *slave;
-	struct net_device *bond_dev = bond->dev;
+	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
 	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
 	unsigned short max_hard_header_len = ETH_HLEN;
 	unsigned int gso_max_size = GSO_MAX_SIZE;
+	struct net_device *bond_dev = bond->dev;
 	u16 gso_max_segs = GSO_MAX_SEGS;
-	int i;
-	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
-
-	read_lock(&bond->lock);
+	struct slave *slave;
 
-	if (!bond->first_slave)
+	if (list_empty(&bond->slave_list))
 		goto done;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		vlan_features = netdev_increment_features(vlan_features,
 			slave->dev->vlan_features, BOND_VLAN_FEATURES);
 
@@ -1378,8 +1148,6 @@ done:
 	flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
 	bond_dev->priv_flags = flags | dst_release_flag;
 
-	read_unlock(&bond->lock);
-
 	netdev_change_features(bond_dev);
 }
 
@@ -1545,7 +1313,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * bond ether type mutual exclusion - don't allow slaves of dissimilar
 	 * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
 	 */
-	if (bond->slave_cnt == 0) {
+	if (list_empty(&bond->slave_list)) {
 		if (bond_dev->type != slave_dev->type) {
 			pr_debug("%s: change device type from %d to %d\n",
 				 bond_dev->name,
@@ -1584,7 +1352,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	}
 
 	if (slave_ops->ndo_set_mac_address == NULL) {
-		if (bond->slave_cnt == 0) {
+		if (list_empty(&bond->slave_list)) {
 			pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.",
 				   bond_dev->name);
 			bond->params.fail_over_mac = BOND_FOM_ACTIVE;
@@ -1600,7 +1368,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	/* If this is the first slave, then we need to set the master's hardware
 	 * address to be the same as the slave's. */
-	if (!bond->slave_cnt && bond->dev->addr_assign_type == NET_ADDR_RANDOM)
+	if (list_empty(&bond->slave_list) &&
+	    bond->dev->addr_assign_type == NET_ADDR_RANDOM)
 		bond_set_dev_addr(bond->dev, slave_dev);
 
 	new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
@@ -1608,7 +1377,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		res = -ENOMEM;
 		goto err_undo_flags;
 	}
-
+	INIT_LIST_HEAD(&new_slave->list);
 	/*
 	 * Set the new_slave's queue_id to be zero.  Queue ID mapping
 	 * is set via sysfs or module option if desired.
@@ -1703,7 +1472,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		dev_mc_add(slave_dev, lacpdu_multicast);
 	}
 
-	bond_add_vlans_on_slave(bond, slave_dev);
+	res = vlan_vids_add_by_dev(slave_dev, bond_dev);
+	if (res) {
+		pr_err("%s: Error: Couldn't add bond vlan ids to %s\n",
+		       bond_dev->name, slave_dev->name);
+		goto err_close;
+	}
 
 	write_lock_bh(&bond->lock);
 
@@ -1794,15 +1568,18 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		 */
 		bond_set_slave_inactive_flags(new_slave);
 		/* if this is the first slave */
-		if (bond->slave_cnt == 1) {
+		if (bond_first_slave(bond) == new_slave) {
 			SLAVE_AD_INFO(new_slave).id = 1;
 			/* Initialize AD with the number of times that the AD timer is called in 1 second
 			 * can be called only after the mac address of the bond is set
 			 */
 			bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL);
 		} else {
+			struct slave *prev_slave;
+
+			prev_slave = bond_prev_slave(bond, new_slave);
 			SLAVE_AD_INFO(new_slave).id =
-				SLAVE_AD_INFO(new_slave->prev).id + 1;
+				SLAVE_AD_INFO(prev_slave).id + 1;
 		}
 
 		bond_3ad_bind_slave(new_slave);
@@ -1824,7 +1601,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		 * so we can change it without calling change_active_interface()
 		 */
 		if (!bond->curr_active_slave && new_slave->link == BOND_LINK_UP)
-			bond->curr_active_slave = new_slave;
+			rcu_assign_pointer(bond->curr_active_slave, new_slave);
 
 		break;
 	} /* switch(bond_mode) */
@@ -1834,7 +1611,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	bond_set_carrier(bond);
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	slave_dev->npinfo = bond_netpoll_info(bond);
+	slave_dev->npinfo = bond->dev->npinfo;
 	if (slave_dev->npinfo) {
 		if (slave_enable_netpoll(new_slave)) {
 			read_unlock(&bond->lock);
@@ -1876,7 +1653,7 @@ err_detach:
 	if (!USES_PRIMARY(bond->params.mode))
 		bond_hw_addr_flush(bond_dev, slave_dev);
 
-	bond_del_vlans_from_slave(bond, slave_dev);
+	vlan_vids_del_by_dev(slave_dev, bond_dev);
 	write_lock_bh(&bond->lock);
 	bond_detach_slave(bond, new_slave);
 	if (bond->primary_slave == new_slave)
@@ -1921,7 +1698,7 @@ err_free:
 err_undo_flags:
 	bond_compute_features(bond);
 	/* Enslave of first slave has failed and we need to fix master's mac */
-	if (bond->slave_cnt == 0 &&
+	if (list_empty(&bond->slave_list) &&
 	    ether_addr_equal(bond_dev->dev_addr, slave_dev->dev_addr))
 		eth_hw_addr_random(bond_dev);
 
@@ -1977,15 +1754,6 @@ static int __bond_release_one(struct net_device *bond_dev,
 	netdev_rx_handler_unregister(slave_dev);
 	write_lock_bh(&bond->lock);
 
-	if (!all && !bond->params.fail_over_mac) {
-		if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) &&
-		    bond->slave_cnt > 1)
-			pr_warning("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
-				   bond_dev->name, slave_dev->name,
-				   slave->perm_hwaddr,
-				   bond_dev->name, slave_dev->name);
-	}
-
 	/* Inform AD package of unbinding of slave. */
 	if (bond->params.mode == BOND_MODE_8023AD) {
 		/* must be called before the slave is
@@ -2006,6 +1774,15 @@ static int __bond_release_one(struct net_device *bond_dev,
 	/* release the slave from its bond */
 	bond_detach_slave(bond, slave);
 
+	if (!all && !bond->params.fail_over_mac) {
+		if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) &&
+		    !list_empty(&bond->slave_list))
+			pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
+				   bond_dev->name, slave_dev->name,
+				   slave->perm_hwaddr,
+				   bond_dev->name, slave_dev->name);
+	}
+
 	if (bond->primary_slave == slave)
 		bond->primary_slave = NULL;
 
@@ -2024,7 +1801,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	}
 
 	if (all) {
-		bond->curr_active_slave = NULL;
+		rcu_assign_pointer(bond->curr_active_slave, NULL);
 	} else if (oldcurrent == slave) {
 		/*
 		 * Note that we hold RTNL over this sequence, so there
@@ -2042,11 +1819,11 @@ static int __bond_release_one(struct net_device *bond_dev,
 		write_lock_bh(&bond->lock);
 	}
 
-	if (bond->slave_cnt == 0) {
+	if (list_empty(&bond->slave_list)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
 
-		if (bond_vlan_used(bond)) {
+		if (vlan_uses_dev(bond_dev)) {
 			pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
 				   bond_dev->name, bond_dev->name);
 			pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
@@ -2056,8 +1833,9 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	write_unlock_bh(&bond->lock);
 	unblock_netpoll_tx();
+	synchronize_rcu();
 
-	if (bond->slave_cnt == 0) {
+	if (list_empty(&bond->slave_list)) {
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
 		call_netdevice_notifiers(NETDEV_RELEASE, bond->dev);
 	}
@@ -2071,7 +1849,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	/* must do this from outside any spinlocks */
 	bond_destroy_slave_symlinks(bond_dev, slave_dev);
 
-	bond_del_vlans_from_slave(bond, slave_dev);
+	vlan_vids_del_by_dev(slave_dev, bond_dev);
 
 	/* If the mode USES_PRIMARY, then this cases was handled above by
 	 * bond_change_active_slave(..., NULL)
@@ -2128,7 +1906,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 	int ret;
 
 	ret = bond_release(bond_dev, slave_dev);
-	if ((ret == 0) && (bond->slave_cnt == 0)) {
+	if (ret == 0 && list_empty(&bond->slave_list)) {
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		pr_info("%s: destroying bond %s.\n",
 			bond_dev->name, bond_dev->name);
@@ -2165,23 +1943,19 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi
 
 	read_lock(&bond->lock);
 
-	read_lock(&bond->curr_slave_lock);
 	old_active = bond->curr_active_slave;
-	read_unlock(&bond->curr_slave_lock);
-
 	new_active = bond_get_slave_by_dev(bond, slave_dev);
-
 	/*
 	 * Changing to the current active: do nothing; return success.
 	 */
-	if (new_active && (new_active == old_active)) {
+	if (new_active && new_active == old_active) {
 		read_unlock(&bond->lock);
 		return 0;
 	}
 
-	if ((new_active) &&
-	    (old_active) &&
-	    (new_active->link == BOND_LINK_UP) &&
+	if (new_active &&
+	    old_active &&
+	    new_active->link == BOND_LINK_UP &&
 	    IS_UP(new_active->dev)) {
 		block_netpoll_tx();
 		write_lock_bh(&bond->curr_slave_lock);
@@ -2213,13 +1987,12 @@ static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
 static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	int i = 0, res = -ENODEV;
 	struct slave *slave;
-	int i, res = -ENODEV;
 
 	read_lock(&bond->lock);
-
-	bond_for_each_slave(bond, slave, i) {
-		if (i == (int)info->slave_id) {
+	bond_for_each_slave(bond, slave) {
+		if (i++ == (int)info->slave_id) {
 			res = 0;
 			strcpy(info->slave_name, slave->dev->name);
 			info->link = slave->link;
@@ -2228,7 +2001,6 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in
 			break;
 		}
 	}
-
 	read_unlock(&bond->lock);
 
 	return res;
@@ -2239,13 +2011,13 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in
 
 static int bond_miimon_inspect(struct bonding *bond)
 {
+	int link_state, commit = 0;
 	struct slave *slave;
-	int i, link_state, commit = 0;
 	bool ignore_updelay;
 
 	ignore_updelay = !bond->curr_active_slave ? true : false;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		slave->new_link = BOND_LINK_NOCHANGE;
 
 		link_state = bond_check_dev_link(bond, slave->dev, 0);
@@ -2340,9 +2112,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 static void bond_miimon_commit(struct bonding *bond)
 {
 	struct slave *slave;
-	int i;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		switch (slave->new_link) {
 		case BOND_LINK_NOCHANGE:
 			continue;
@@ -2447,7 +2218,7 @@ void bond_mii_monitor(struct work_struct *work)
 
 	delay = msecs_to_jiffies(bond->params.miimon);
 
-	if (bond->slave_cnt == 0)
+	if (list_empty(&bond->slave_list))
 		goto re_arm;
 
 	should_notify_peers = bond_should_notify_peers(bond);
@@ -2479,35 +2250,32 @@ re_arm:
 	read_unlock(&bond->lock);
 
 	if (should_notify_peers) {
-		if (!rtnl_trylock()) {
-			read_lock(&bond->lock);
-			bond->send_peer_notif++;
-			read_unlock(&bond->lock);
+		if (!rtnl_trylock())
 			return;
-		}
 		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
 		rtnl_unlock();
 	}
 }
 
-static int bond_has_this_ip(struct bonding *bond, __be32 ip)
+static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
 {
-	struct vlan_entry *vlan;
-	struct net_device *vlan_dev;
+	struct net_device *upper;
+	struct list_head *iter;
+	bool ret = false;
 
 	if (ip == bond_confirm_addr(bond->dev, 0, ip))
-		return 1;
+		return true;
 
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		rcu_read_lock();
-		vlan_dev = __vlan_find_dev_deep(bond->dev, htons(ETH_P_8021Q),
-						vlan->vlan_id);
-		rcu_read_unlock();
-		if (vlan_dev && ip == bond_confirm_addr(vlan_dev, 0, ip))
-			return 1;
+	rcu_read_lock();
+	netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+		if (ip == bond_confirm_addr(upper, 0, ip)) {
+			ret = true;
+			break;
+		}
 	}
+	rcu_read_unlock();
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -2542,81 +2310,79 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_
 
 static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 {
-	int i, vlan_id;
-	__be32 *targets = bond->params.arp_targets;
-	struct vlan_entry *vlan;
-	struct net_device *vlan_dev = NULL;
+	struct net_device *upper, *vlan_upper;
+	struct list_head *iter, *vlan_iter;
 	struct rtable *rt;
+	__be32 *targets = bond->params.arp_targets, addr;
+	int i, vlan_id;
 
-	for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
-		__be32 addr;
-		if (!targets[i])
-			break;
+	for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
 		pr_debug("basa: target %pI4\n", &targets[i]);
-		if (!bond_vlan_used(bond)) {
-			pr_debug("basa: empty vlan: arp_send\n");
-			addr = bond_confirm_addr(bond->dev, targets[i], 0);
-			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
-				      addr, 0);
-			continue;
-		}
 
-		/*
-		 * If VLANs are configured, we do a route lookup to
-		 * determine which VLAN interface would be used, so we
-		 * can tag the ARP with the proper VLAN tag.
-		 */
+		/* Find out through which dev should the packet go */
 		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
 				     RTO_ONLINK, 0);
 		if (IS_ERR(rt)) {
-			if (net_ratelimit()) {
-				pr_warning("%s: no route to arp_ip_target %pI4\n",
-					   bond->dev->name, &targets[i]);
-			}
+			pr_debug("%s: no route to arp_ip_target %pI4\n",
+				 bond->dev->name, &targets[i]);
 			continue;
 		}
 
-		/*
-		 * This target is not on a VLAN
+		vlan_id = 0;
+
+		/* bond device itself */
+		if (rt->dst.dev == bond->dev)
+			goto found;
+
+		rcu_read_lock();
+		/* first we search only for vlan devices. for every vlan
+		 * found we verify its upper dev list, searching for the
+		 * rt->dst.dev. If found we save the tag of the vlan and
+		 * proceed to send the packet.
+		 *
+		 * TODO: QinQ?
 		 */
-		if (rt->dst.dev == bond->dev) {
-			ip_rt_put(rt);
-			pr_debug("basa: rtdev == bond->dev: arp_send\n");
-			addr = bond_confirm_addr(bond->dev, targets[i], 0);
-			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
-				      addr, 0);
-			continue;
+		netdev_for_each_upper_dev_rcu(bond->dev, vlan_upper, vlan_iter) {
+			if (!is_vlan_dev(vlan_upper))
+				continue;
+			netdev_for_each_upper_dev_rcu(vlan_upper, upper, iter) {
+				if (upper == rt->dst.dev) {
+					vlan_id = vlan_dev_vlan_id(vlan_upper);
+					rcu_read_unlock();
+					goto found;
+				}
+			}
 		}
 
-		vlan_id = 0;
-		list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-			rcu_read_lock();
-			vlan_dev = __vlan_find_dev_deep(bond->dev,
-							htons(ETH_P_8021Q),
-							vlan->vlan_id);
-			rcu_read_unlock();
-			if (vlan_dev == rt->dst.dev) {
-				vlan_id = vlan->vlan_id;
-				pr_debug("basa: vlan match on %s %d\n",
-				       vlan_dev->name, vlan_id);
-				break;
+		/* if the device we're looking for is not on top of any of
+		 * our upper vlans, then just search for any dev that
+		 * matches, and in case it's a vlan - save the id
+		 */
+		netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+			if (upper == rt->dst.dev) {
+				/* if it's a vlan - get its VID */
+				if (is_vlan_dev(upper))
+					vlan_id = vlan_dev_vlan_id(upper);
+
+				rcu_read_unlock();
+				goto found;
 			}
 		}
+		rcu_read_unlock();
 
-		if (vlan_id && vlan_dev) {
-			ip_rt_put(rt);
-			addr = bond_confirm_addr(vlan_dev, targets[i], 0);
-			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
-				      addr, vlan_id);
-			continue;
-		}
+		/* Not our device - skip */
+		pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
+			 bond->dev->name, &targets[i],
+			 rt->dst.dev ? rt->dst.dev->name : "NULL");
 
-		if (net_ratelimit()) {
-			pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
-				   bond->dev->name, &targets[i],
-				   rt->dst.dev ? rt->dst.dev->name : "NULL");
-		}
 		ip_rt_put(rt);
+		continue;
+
+found:
+		addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
+		ip_rt_put(rt);
+		bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
+			      addr, vlan_id);
 	}
 }
 
@@ -2713,6 +2479,20 @@ out_unlock:
 	return RX_HANDLER_ANOTHER;
 }
 
+/* function to verify if we're in the arp_interval timeslice, returns true if
+ * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval +
+ * arp_interval/2) . the arp_interval/2 is needed for really fast networks.
+ */
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod)
+{
+	int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
+
+	return time_in_range(jiffies,
+			     last_act - delta_in_ticks,
+			     last_act + mod * delta_in_ticks + delta_in_ticks/2);
+}
+
 /*
  * this function is called regularly to monitor each slave's link
  * ensuring that traffic is being sent and received when arp monitoring
@@ -2726,21 +2506,13 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 					    arp_work.work);
 	struct slave *slave, *oldcurrent;
 	int do_failover = 0;
-	int delta_in_ticks, extra_ticks;
-	int i;
 
 	read_lock(&bond->lock);
 
-	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
-	extra_ticks = delta_in_ticks / 2;
-
-	if (bond->slave_cnt == 0)
+	if (list_empty(&bond->slave_list))
 		goto re_arm;
 
-	read_lock(&bond->curr_slave_lock);
 	oldcurrent = bond->curr_active_slave;
-	read_unlock(&bond->curr_slave_lock);
-
 	/* see if any of the previous devices are up now (i.e. they have
 	 * xmt and rcv traffic). the curr_active_slave does not come into
 	 * the picture unless it is null. also, slave->jiffies is not needed
@@ -2749,16 +2521,12 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 	 * TODO: what about up/down delay in arp mode? it wasn't here before
 	 *       so it can wait
 	 */
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
 		if (slave->link != BOND_LINK_UP) {
-			if (time_in_range(jiffies,
-				trans_start - delta_in_ticks,
-				trans_start + delta_in_ticks + extra_ticks) &&
-			    time_in_range(jiffies,
-				slave->dev->last_rx - delta_in_ticks,
-				slave->dev->last_rx + delta_in_ticks + extra_ticks)) {
+			if (bond_time_in_interval(bond, trans_start, 1) &&
+			    bond_time_in_interval(bond, slave->dev->last_rx, 1)) {
 
 				slave->link  = BOND_LINK_UP;
 				bond_set_active_slave(slave);
@@ -2786,12 +2554,8 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 			 * when the source ip is 0, so don't take the link down
 			 * if we don't know our ip yet
 			 */
-			if (!time_in_range(jiffies,
-				trans_start - delta_in_ticks,
-				trans_start + 2 * delta_in_ticks + extra_ticks) ||
-			    !time_in_range(jiffies,
-				slave->dev->last_rx - delta_in_ticks,
-				slave->dev->last_rx + 2 * delta_in_ticks + extra_ticks)) {
+			if (!bond_time_in_interval(bond, trans_start, 2) ||
+			    !bond_time_in_interval(bond, slave->dev->last_rx, 2)) {
 
 				slave->link  = BOND_LINK_DOWN;
 				bond_set_backup_slave(slave);
@@ -2831,7 +2595,8 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 
 re_arm:
 	if (bond->params.arp_interval)
-		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
+		queue_delayed_work(bond->wq, &bond->arp_work,
+				   msecs_to_jiffies(bond->params.arp_interval));
 
 	read_unlock(&bond->lock);
 }
@@ -2844,32 +2609,21 @@ re_arm:
  *
  * Called with bond->lock held for read.
  */
-static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
+static int bond_ab_arp_inspect(struct bonding *bond)
 {
+	unsigned long trans_start, last_rx;
 	struct slave *slave;
-	int i, commit = 0;
-	unsigned long trans_start;
-	int extra_ticks;
-
-	/* All the time comparisons below need some extra time. Otherwise, on
-	 * fast networks the ARP probe/reply may arrive within the same jiffy
-	 * as it was sent.  Then, the next time the ARP monitor is run, one
-	 * arp_interval will already have passed in the comparisons.
-	 */
-	extra_ticks = delta_in_ticks / 2;
+	int commit = 0;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		slave->new_link = BOND_LINK_NOCHANGE;
+		last_rx = slave_last_rx(bond, slave);
 
 		if (slave->link != BOND_LINK_UP) {
-			if (time_in_range(jiffies,
-				slave_last_rx(bond, slave) - delta_in_ticks,
-				slave_last_rx(bond, slave) + delta_in_ticks + extra_ticks)) {
-
+			if (bond_time_in_interval(bond, last_rx, 1)) {
 				slave->new_link = BOND_LINK_UP;
 				commit++;
 			}
-
 			continue;
 		}
 
@@ -2878,9 +2632,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
 		 * active.  This avoids bouncing, as the last receive
 		 * times need a full ARP monitor cycle to be updated.
 		 */
-		if (time_in_range(jiffies,
-				  slave->jiffies - delta_in_ticks,
-				  slave->jiffies + 2 * delta_in_ticks + extra_ticks))
+		if (bond_time_in_interval(bond, slave->jiffies, 2))
 			continue;
 
 		/*
@@ -2898,10 +2650,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
 		 */
 		if (!bond_is_active_slave(slave) &&
 		    !bond->current_arp_slave &&
-		    !time_in_range(jiffies,
-			slave_last_rx(bond, slave) - delta_in_ticks,
-			slave_last_rx(bond, slave) + 3 * delta_in_ticks + extra_ticks)) {
-
+		    !bond_time_in_interval(bond, last_rx, 3)) {
 			slave->new_link = BOND_LINK_DOWN;
 			commit++;
 		}
@@ -2914,13 +2663,8 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
 		 */
 		trans_start = dev_trans_start(slave->dev);
 		if (bond_is_active_slave(slave) &&
-		    (!time_in_range(jiffies,
-			trans_start - delta_in_ticks,
-			trans_start + 2 * delta_in_ticks + extra_ticks) ||
-		     !time_in_range(jiffies,
-			slave_last_rx(bond, slave) - delta_in_ticks,
-			slave_last_rx(bond, slave) + 2 * delta_in_ticks + extra_ticks))) {
-
+		    (!bond_time_in_interval(bond, trans_start, 2) ||
+		     !bond_time_in_interval(bond, last_rx, 2))) {
 			slave->new_link = BOND_LINK_DOWN;
 			commit++;
 		}
@@ -2935,24 +2679,21 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks)
  *
  * Called with RTNL and bond->lock for read.
  */
-static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks)
+static void bond_ab_arp_commit(struct bonding *bond)
 {
-	struct slave *slave;
-	int i;
 	unsigned long trans_start;
+	struct slave *slave;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		switch (slave->new_link) {
 		case BOND_LINK_NOCHANGE:
 			continue;
 
 		case BOND_LINK_UP:
 			trans_start = dev_trans_start(slave->dev);
-			if ((!bond->curr_active_slave &&
-			     time_in_range(jiffies,
-					   trans_start - delta_in_ticks,
-					   trans_start + delta_in_ticks + delta_in_ticks / 2)) ||
-			    bond->curr_active_slave != slave) {
+			if (bond->curr_active_slave != slave ||
+			    (!bond->curr_active_slave &&
+			     bond_time_in_interval(bond, trans_start, 1))) {
 				slave->link = BOND_LINK_UP;
 				if (bond->current_arp_slave) {
 					bond_set_slave_inactive_flags(
@@ -3014,7 +2755,7 @@ do_failover:
  */
 static void bond_ab_arp_probe(struct bonding *bond)
 {
-	struct slave *slave;
+	struct slave *slave, *next_slave;
 	int i;
 
 	read_lock(&bond->curr_slave_lock);
@@ -3038,7 +2779,7 @@ static void bond_ab_arp_probe(struct bonding *bond)
 	 */
 
 	if (!bond->current_arp_slave) {
-		bond->current_arp_slave = bond->first_slave;
+		bond->current_arp_slave = bond_first_slave(bond);
 		if (!bond->current_arp_slave)
 			return;
 	}
@@ -3046,7 +2787,8 @@ static void bond_ab_arp_probe(struct bonding *bond)
 	bond_set_slave_inactive_flags(bond->current_arp_slave);
 
 	/* search for next candidate */
-	bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) {
+	next_slave = bond_next_slave(bond, bond->current_arp_slave);
+	bond_for_each_slave_from(bond, slave, i, next_slave) {
 		if (IS_UP(slave->dev)) {
 			slave->link = BOND_LINK_BACK;
 			bond_set_slave_active_flags(slave);
@@ -3087,12 +2829,12 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 
 	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
 
-	if (bond->slave_cnt == 0)
+	if (list_empty(&bond->slave_list))
 		goto re_arm;
 
 	should_notify_peers = bond_should_notify_peers(bond);
 
-	if (bond_ab_arp_inspect(bond, delta_in_ticks)) {
+	if (bond_ab_arp_inspect(bond)) {
 		read_unlock(&bond->lock);
 
 		/* Race avoidance with bond_close flush of workqueue */
@@ -3105,7 +2847,7 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 
 		read_lock(&bond->lock);
 
-		bond_ab_arp_commit(bond, delta_in_ticks);
+		bond_ab_arp_commit(bond);
 
 		read_unlock(&bond->lock);
 		rtnl_unlock();
@@ -3121,12 +2863,8 @@ re_arm:
 	read_unlock(&bond->lock);
 
 	if (should_notify_peers) {
-		if (!rtnl_trylock()) {
-			read_lock(&bond->lock);
-			bond->send_peer_notif++;
-			read_unlock(&bond->lock);
+		if (!rtnl_trylock())
 			return;
-		}
 		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
 		rtnl_unlock();
 	}
@@ -3161,6 +2899,10 @@ static int bond_master_netdev_event(unsigned long event,
 	case NETDEV_REGISTER:
 		bond_create_proc_entry(event_bond);
 		break;
+	case NETDEV_NOTIFY_PEERS:
+		if (event_bond->send_peer_notif)
+			event_bond->send_peer_notif--;
+		break;
 	default:
 		break;
 	}
@@ -3234,6 +2976,10 @@ static int bond_slave_netdev_event(unsigned long event,
 	case NETDEV_FEAT_CHANGE:
 		bond_compute_features(bond);
 		break;
+	case NETDEV_RESEND_IGMP:
+		/* Propagate to master device */
+		call_netdevice_notifiers(event, slave->bond->dev);
+		break;
 	default:
 		break;
 	}
@@ -3403,13 +3149,12 @@ static int bond_open(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
-	int i;
 
 	/* reset slave->backup and slave->inactive */
 	read_lock(&bond->lock);
-	if (bond->slave_cnt > 0) {
+	if (!list_empty(&bond->slave_list)) {
 		read_lock(&bond->curr_slave_lock);
-		bond_for_each_slave(bond, slave, i) {
+		bond_for_each_slave(bond, slave) {
 			if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
 				&& (slave != bond->curr_active_slave)) {
 				bond_set_slave_inactive_flags(slave);
@@ -3455,17 +3200,10 @@ static int bond_close(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 
-	write_lock_bh(&bond->lock);
-	bond->send_peer_notif = 0;
-	write_unlock_bh(&bond->lock);
-
 	bond_work_cancel_all(bond);
-	if (bond_is_lb(bond)) {
-		/* Must be called only after all
-		 * slaves have been released
-		 */
+	bond->send_peer_notif = 0;
+	if (bond_is_lb(bond))
 		bond_alb_deinitialize(bond);
-	}
 	bond->recv_probe = NULL;
 
 	return 0;
@@ -3477,13 +3215,11 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct rtnl_link_stats64 temp;
 	struct slave *slave;
-	int i;
 
 	memset(stats, 0, sizeof(*stats));
 
 	read_lock_bh(&bond->lock);
-
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		const struct rtnl_link_stats64 *sstats =
 			dev_get_stats(slave->dev, &temp);
 
@@ -3513,7 +3249,6 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
 		stats->tx_window_errors += sstats->tx_window_errors;
 	}
-
 	read_unlock_bh(&bond->lock);
 
 	return stats;
@@ -3652,41 +3387,35 @@ static void bond_set_rx_mode(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
-	int i;
 
-	read_lock(&bond->lock);
+	ASSERT_RTNL();
 
 	if (USES_PRIMARY(bond->params.mode)) {
-		read_lock(&bond->curr_slave_lock);
-		slave = bond->curr_active_slave;
+		slave = rtnl_dereference(bond->curr_active_slave);
 		if (slave) {
 			dev_uc_sync(slave->dev, bond_dev);
 			dev_mc_sync(slave->dev, bond_dev);
 		}
-		read_unlock(&bond->curr_slave_lock);
 	} else {
-		bond_for_each_slave(bond, slave, i) {
+		bond_for_each_slave(bond, slave) {
 			dev_uc_sync_multiple(slave->dev, bond_dev);
 			dev_mc_sync_multiple(slave->dev, bond_dev);
 		}
 	}
-
-	read_unlock(&bond->lock);
 }
 
 static int bond_neigh_init(struct neighbour *n)
 {
 	struct bonding *bond = netdev_priv(n->dev);
-	struct slave *slave = bond->first_slave;
 	const struct net_device_ops *slave_ops;
 	struct neigh_parms parms;
+	struct slave *slave;
 	int ret;
 
+	slave = bond_first_slave(bond);
 	if (!slave)
 		return 0;
-
 	slave_ops = slave->dev->netdev_ops;
-
 	if (!slave_ops->ndo_neigh_setup)
 		return 0;
 
@@ -3735,9 +3464,8 @@ static int bond_neigh_setup(struct net_device *dev,
 static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave, *stop_at;
+	struct slave *slave;
 	int res = 0;
-	int i;
 
 	pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond,
 		 (bond_dev ? bond_dev->name : "None"), new_mtu);
@@ -3757,10 +3485,10 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
 	 * call to the base driver.
 	 */
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		pr_debug("s %p s->p %p c_m %p\n",
 			 slave,
-			 slave->prev,
+			 bond_prev_slave(bond, slave),
 			 slave->dev->netdev_ops->ndo_change_mtu);
 
 		res = dev_set_mtu(slave->dev, new_mtu);
@@ -3785,8 +3513,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
 
 unwind:
 	/* unwind from head to the slave that failed */
-	stop_at = slave;
-	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) {
+	bond_for_each_slave_continue_reverse(bond, slave) {
 		int tmp_res;
 
 		tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu);
@@ -3810,9 +3537,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct sockaddr *sa = addr, tmp_sa;
-	struct slave *slave, *stop_at;
+	struct slave *slave;
 	int res = 0;
-	int i;
 
 	if (bond->params.mode == BOND_MODE_ALB)
 		return bond_alb_set_mac_address(bond_dev, addr);
@@ -3845,7 +3571,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	 * call to the base driver.
 	 */
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		const struct net_device_ops *slave_ops = slave->dev->netdev_ops;
 		pr_debug("slave %p %s\n", slave, slave->dev->name);
 
@@ -3877,8 +3603,7 @@ unwind:
 	tmp_sa.sa_family = bond_dev->type;
 
 	/* unwind from head to the slave that failed */
-	stop_at = slave;
-	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) {
+	bond_for_each_slave_continue_reverse(bond, slave) {
 		int tmp_res;
 
 		tmp_res = dev_set_mac_address(slave->dev, &tmp_sa);
@@ -3891,12 +3616,50 @@ unwind:
 	return res;
 }
 
+/**
+ * bond_xmit_slave_id - transmit skb through slave with slave_id
+ * @bond: bonding device that is transmitting
+ * @skb: buffer to transmit
+ * @slave_id: slave id up to slave_cnt-1 through which to transmit
+ *
+ * This function tries to transmit through slave with slave_id but in case
+ * it fails, it tries to find the first available slave for transmission.
+ * The skb is consumed in all cases, thus the function is void.
+ */
+void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id)
+{
+	struct slave *slave;
+	int i = slave_id;
+
+	/* Here we start from the slave with slave_id */
+	bond_for_each_slave_rcu(bond, slave) {
+		if (--i < 0) {
+			if (slave_can_tx(slave)) {
+				bond_dev_queue_xmit(bond, skb, slave->dev);
+				return;
+			}
+		}
+	}
+
+	/* Here we start from the first slave up to slave_id */
+	i = slave_id;
+	bond_for_each_slave_rcu(bond, slave) {
+		if (--i < 0)
+			break;
+		if (slave_can_tx(slave)) {
+			bond_dev_queue_xmit(bond, skb, slave->dev);
+			return;
+		}
+	}
+	/* no slave that can tx has been found */
+	kfree_skb(skb);
+}
+
 static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave, *start_at;
-	int i, slave_no, res = 1;
 	struct iphdr *iph = ip_hdr(skb);
+	struct slave *slave;
 
 	/*
 	 * Start with the curr_active_slave that joined the bond as the
@@ -3905,50 +3668,20 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev
 	 * send the join/membership reports.  The curr_active_slave found
 	 * will send all of this type of traffic.
 	 */
-	if ((iph->protocol == IPPROTO_IGMP) &&
-	    (skb->protocol == htons(ETH_P_IP))) {
-
-		read_lock(&bond->curr_slave_lock);
-		slave = bond->curr_active_slave;
-		read_unlock(&bond->curr_slave_lock);
-
-		if (!slave)
-			goto out;
+	if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) {
+		slave = rcu_dereference(bond->curr_active_slave);
+		if (slave && slave_can_tx(slave))
+			bond_dev_queue_xmit(bond, skb, slave->dev);
+		else
+			bond_xmit_slave_id(bond, skb, 0);
 	} else {
-		/*
-		 * Concurrent TX may collide on rr_tx_counter; we accept
-		 * that as being rare enough not to justify using an
-		 * atomic op here.
-		 */
-		slave_no = bond->rr_tx_counter++ % bond->slave_cnt;
-
-		bond_for_each_slave(bond, slave, i) {
-			slave_no--;
-			if (slave_no < 0)
-				break;
-		}
-	}
-
-	start_at = slave;
-	bond_for_each_slave_from(bond, slave, i, start_at) {
-		if (IS_UP(slave->dev) &&
-		    (slave->link == BOND_LINK_UP) &&
-		    bond_is_active_slave(slave)) {
-			res = bond_dev_queue_xmit(bond, skb, slave->dev);
-			break;
-		}
-	}
-
-out:
-	if (res) {
-		/* no suitable interface, frame not sent */
-		kfree_skb(skb);
+		bond_xmit_slave_id(bond, skb,
+				   bond->rr_tx_counter++ % bond->slave_cnt);
 	}
 
 	return NETDEV_TX_OK;
 }
 
-
 /*
  * in active-backup mode, we know that bond->curr_active_slave is always valid if
  * the bond has a usable interface.
@@ -3956,18 +3689,12 @@ out:
 static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	int res = 1;
-
-	read_lock(&bond->curr_slave_lock);
-
-	if (bond->curr_active_slave)
-		res = bond_dev_queue_xmit(bond, skb,
-			bond->curr_active_slave->dev);
-
-	read_unlock(&bond->curr_slave_lock);
+	struct slave *slave;
 
-	if (res)
-		/* no suitable interface, frame not sent */
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave)
+		bond_dev_queue_xmit(bond, skb, slave->dev);
+	else
 		kfree_skb(skb);
 
 	return NETDEV_TX_OK;
@@ -3981,87 +3708,39 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d
 static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave, *start_at;
-	int slave_no;
-	int i;
-	int res = 1;
 
-	slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt);
-
-	bond_for_each_slave(bond, slave, i) {
-		slave_no--;
-		if (slave_no < 0)
-			break;
-	}
-
-	start_at = slave;
-
-	bond_for_each_slave_from(bond, slave, i, start_at) {
-		if (IS_UP(slave->dev) &&
-		    (slave->link == BOND_LINK_UP) &&
-		    bond_is_active_slave(slave)) {
-			res = bond_dev_queue_xmit(bond, skb, slave->dev);
-			break;
-		}
-	}
-
-	if (res) {
-		/* no suitable interface, frame not sent */
-		kfree_skb(skb);
-	}
+	bond_xmit_slave_id(bond, skb,
+			   bond->xmit_hash_policy(skb, bond->slave_cnt));
 
 	return NETDEV_TX_OK;
 }
 
-/*
- * in broadcast mode, we send everything to all usable interfaces.
- */
+/* in broadcast mode, we send everything to all usable interfaces. */
 static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave, *start_at;
-	struct net_device *tx_dev = NULL;
-	int i;
-	int res = 1;
-
-	read_lock(&bond->curr_slave_lock);
-	start_at = bond->curr_active_slave;
-	read_unlock(&bond->curr_slave_lock);
-
-	if (!start_at)
-		goto out;
+	struct slave *slave = NULL;
 
-	bond_for_each_slave_from(bond, slave, i, start_at) {
-		if (IS_UP(slave->dev) &&
-		    (slave->link == BOND_LINK_UP) &&
-		    bond_is_active_slave(slave)) {
-			if (tx_dev) {
-				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
-				if (!skb2) {
-					pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n",
-					       bond_dev->name);
-					continue;
-				}
+	bond_for_each_slave_rcu(bond, slave) {
+		if (bond_is_last_slave(bond, slave))
+			break;
+		if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP) {
+			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
-				res = bond_dev_queue_xmit(bond, skb2, tx_dev);
-				if (res) {
-					kfree_skb(skb2);
-					continue;
-				}
+			if (!skb2) {
+				pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n",
+				       bond_dev->name);
+				continue;
 			}
-			tx_dev = slave->dev;
+			/* bond_dev_queue_xmit always returns 0 */
+			bond_dev_queue_xmit(bond, skb2, slave->dev);
 		}
 	}
-
-	if (tx_dev)
-		res = bond_dev_queue_xmit(bond, skb, tx_dev);
-
-out:
-	if (res)
-		/* no suitable interface, frame not sent */
+	if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP)
+		bond_dev_queue_xmit(bond, skb, slave->dev);
+	else
 		kfree_skb(skb);
 
-	/* frame sent to all suitable interfaces */
 	return NETDEV_TX_OK;
 }
 
@@ -4089,15 +3768,15 @@ static void bond_set_xmit_hash_policy(struct bonding *bond)
 static inline int bond_slave_override(struct bonding *bond,
 				      struct sk_buff *skb)
 {
-	int i, res = 1;
 	struct slave *slave = NULL;
 	struct slave *check_slave;
+	int res = 1;
 
 	if (!skb->queue_mapping)
 		return 1;
 
 	/* Find out if any slaves have the same mapping as this skb. */
-	bond_for_each_slave(bond, check_slave, i) {
+	bond_for_each_slave_rcu(bond, check_slave) {
 		if (check_slave->queue_id == skb->queue_mapping) {
 			slave = check_slave;
 			break;
@@ -4182,14 +3861,12 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (is_netpoll_tx_blocked(dev))
 		return NETDEV_TX_BUSY;
 
-	read_lock(&bond->lock);
-
-	if (bond->slave_cnt)
+	rcu_read_lock();
+	if (!list_empty(&bond->slave_list))
 		ret = __bond_start_xmit(skb, dev);
 	else
 		kfree_skb(skb);
-
-	read_unlock(&bond->lock);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -4230,9 +3907,8 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev,
 				     struct ethtool_cmd *ecmd)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave;
-	int i;
 	unsigned long speed = 0;
+	struct slave *slave;
 
 	ecmd->duplex = DUPLEX_UNKNOWN;
 	ecmd->port = PORT_OTHER;
@@ -4243,7 +3919,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev,
 	 * this is an accurate maximum.
 	 */
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (SLAVE_IS_OK(slave)) {
 			if (slave->speed != SPEED_UNKNOWN)
 				speed += slave->speed;
@@ -4254,6 +3930,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev,
 	}
 	ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN);
 	read_unlock(&bond->lock);
+
 	return 0;
 }
 
@@ -4317,12 +3994,11 @@ static void bond_setup(struct net_device *bond_dev)
 	/* initialize rwlocks */
 	rwlock_init(&bond->lock);
 	rwlock_init(&bond->curr_slave_lock);
-
+	INIT_LIST_HEAD(&bond->slave_list);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
 	bond->dev = bond_dev;
-	INIT_LIST_HEAD(&bond->vlan_list);
 
 	/* Initialize the device entry points */
 	ether_setup(bond_dev);
@@ -4374,23 +4050,18 @@ static void bond_setup(struct net_device *bond_dev)
 static void bond_uninit(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct vlan_entry *vlan, *tmp;
+	struct slave *slave, *tmp_slave;
 
 	bond_netpoll_cleanup(bond_dev);
 
 	/* Release the bonded slaves */
-	while (bond->first_slave != NULL)
-		__bond_release_one(bond_dev, bond->first_slave->dev, true);
+	list_for_each_entry_safe(slave, tmp_slave, &bond->slave_list, list)
+		__bond_release_one(bond_dev, slave->dev, true);
 	pr_info("%s: released all slaves\n", bond_dev->name);
 
 	list_del(&bond->bond_list);
 
 	bond_debug_unregister(bond);
-
-	list_for_each_entry_safe(vlan, tmp, &bond->vlan_list, vlan_list) {
-		list_del(&vlan->vlan_list);
-		kfree(vlan);
-	}
 }
 
 /*------------------------- Module initialization ---------------------------*/

drivers/net/bonding/bond_procfs.c

@@ -12,7 +12,6 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 	struct bonding *bond = seq->private;
 	loff_t off = 0;
 	struct slave *slave;
-	int i;
 
 	/* make sure the bond won't be taken away */
 	rcu_read_lock();
@@ -21,10 +20,9 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave)
 		if (++off == *pos)
 			return slave;
-	}
 
 	return NULL;
 }
@@ -36,11 +34,13 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
-		return bond->first_slave;
+		return bond_first_slave(bond);
 
-	slave = slave->next;
+	if (bond_is_last_slave(bond, slave))
+		return NULL;
+	slave = bond_next_slave(bond, slave);
 
-	return (slave == bond->first_slave) ? NULL : slave;
+	return slave;
 }
 
 static void bond_info_seq_stop(struct seq_file *seq, void *v)

drivers/net/bonding/bond_sysfs.c

@@ -209,12 +209,12 @@ void bond_destroy_slave_symlinks(struct net_device *master,
 static ssize_t bonding_show_slaves(struct device *d,
 				   struct device_attribute *attr, char *buf)
 {
-	struct slave *slave;
-	int i, res = 0;
 	struct bonding *bond = to_bond(d);
+	struct slave *slave;
+	int res = 0;
 
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (res > (PAGE_SIZE - IFNAMSIZ)) {
 			/* not enough space for another interface name */
 			if ((PAGE_SIZE - res) > 10)
@@ -227,6 +227,7 @@ static ssize_t bonding_show_slaves(struct device *d,
 	read_unlock(&bond->lock);
 	if (res)
 		buf[res-1] = '\n'; /* eat the leftover space */
+
 	return res;
 }
 
@@ -325,7 +326,7 @@ static ssize_t bonding_store_mode(struct device *d,
 		goto out;
 	}
 
-	if (bond->slave_cnt > 0) {
+	if (!list_empty(&bond->slave_list)) {
 		pr_err("unable to update mode of %s because it has slaves.\n",
 			bond->dev->name);
 		ret = -EPERM;
@@ -501,20 +502,25 @@ static ssize_t bonding_store_fail_over_mac(struct device *d,
 					   struct device_attribute *attr,
 					   const char *buf, size_t count)
 {
-	int new_value;
+	int new_value, ret = count;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->slave_cnt != 0) {
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (!list_empty(&bond->slave_list)) {
 		pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n",
 		       bond->dev->name);
-		return -EPERM;
+		ret = -EPERM;
+		goto out;
 	}
 
 	new_value = bond_parse_parm(buf, fail_over_mac_tbl);
 	if (new_value < 0) {
 		pr_err("%s: Ignoring invalid fail_over_mac value %s.\n",
 		       bond->dev->name, buf);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	bond->params.fail_over_mac = new_value;
@@ -522,7 +528,9 @@ static ssize_t bonding_store_fail_over_mac(struct device *d,
 		bond->dev->name, fail_over_mac_tbl[new_value].modename,
 		new_value);
 
-	return count;
+out:
+	rtnl_unlock();
+	return ret;
 }
 
 static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR,
@@ -661,7 +669,7 @@ static ssize_t bonding_store_arp_targets(struct device *d,
 			 &newtarget);
 		/* not to race with bond_arp_rcv */
 		write_lock_bh(&bond->lock);
-		bond_for_each_slave(bond, slave, i)
+		bond_for_each_slave(bond, slave)
 			slave->target_last_arp_rx[ind] = jiffies;
 		targets[ind] = newtarget;
 		write_unlock_bh(&bond->lock);
@@ -687,7 +695,7 @@ static ssize_t bonding_store_arp_targets(struct device *d,
 			&newtarget);
 
 		write_lock_bh(&bond->lock);
-		bond_for_each_slave(bond, slave, i) {
+		bond_for_each_slave(bond, slave) {
 			targets_rx = slave->target_last_arp_rx;
 			j = ind;
 			for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
@@ -844,8 +852,11 @@ static ssize_t bonding_store_lacp(struct device *d,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
-	int new_value, ret = count;
 	struct bonding *bond = to_bond(d);
+	int new_value, ret = count;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
 
 	if (bond->dev->flags & IFF_UP) {
 		pr_err("%s: Unable to update LACP rate because interface is up.\n",
@@ -875,6 +886,8 @@ static ssize_t bonding_store_lacp(struct device *d,
 		ret = -EINVAL;
 	}
 out:
+	rtnl_unlock();
+
 	return ret;
 }
 static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR,
@@ -1078,10 +1091,9 @@ static ssize_t bonding_store_primary(struct device *d,
 				     struct device_attribute *attr,
 				     const char *buf, size_t count)
 {
-	int i;
-	struct slave *slave;
 	struct bonding *bond = to_bond(d);
 	char ifname[IFNAMSIZ];
+	struct slave *slave;
 
 	if (!rtnl_trylock())
 		return restart_syscall();
@@ -1107,7 +1119,7 @@ static ssize_t bonding_store_primary(struct device *d,
 		goto out;
 	}
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) {
 			pr_info("%s: Setting %s as primary slave.\n",
 				bond->dev->name, slave->dev->name);
@@ -1236,16 +1248,16 @@ static ssize_t bonding_show_active_slave(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct slave *curr;
 	struct bonding *bond = to_bond(d);
+	struct slave *curr;
 	int count = 0;
 
-	read_lock(&bond->curr_slave_lock);
-	curr = bond->curr_active_slave;
-	read_unlock(&bond->curr_slave_lock);
-
+	rcu_read_lock();
+	curr = rcu_dereference(bond->curr_active_slave);
 	if (USES_PRIMARY(bond->params.mode) && curr)
 		count = sprintf(buf, "%s\n", curr->dev->name);
+	rcu_read_unlock();
+
 	return count;
 }
 
@@ -1253,16 +1265,14 @@ static ssize_t bonding_store_active_slave(struct device *d,
 					  struct device_attribute *attr,
 					  const char *buf, size_t count)
 {
-	int i;
-	struct slave *slave;
-	struct slave *old_active = NULL;
-	struct slave *new_active = NULL;
+	struct slave *slave, *old_active, *new_active;
 	struct bonding *bond = to_bond(d);
 	char ifname[IFNAMSIZ];
 
 	if (!rtnl_trylock())
 		return restart_syscall();
 
+	old_active = new_active = NULL;
 	block_netpoll_tx();
 	read_lock(&bond->lock);
 	write_lock_bh(&bond->curr_slave_lock);
@@ -1279,12 +1289,12 @@ static ssize_t bonding_store_active_slave(struct device *d,
 	if (!strlen(ifname) || buf[0] == '\n') {
 		pr_info("%s: Clearing current active slave.\n",
 			bond->dev->name);
-		bond->curr_active_slave = NULL;
+		rcu_assign_pointer(bond->curr_active_slave, NULL);
 		bond_select_active_slave(bond);
 		goto out;
 	}
 
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) {
 			old_active = bond->curr_active_slave;
 			new_active = slave;
@@ -1295,8 +1305,7 @@ static ssize_t bonding_store_active_slave(struct device *d,
 					bond->dev->name,
 					slave->dev->name);
 				goto out;
-			}
-			else {
+			} else {
 				if ((new_active) &&
 				    (old_active) &&
 				    (new_active->link == BOND_LINK_UP) &&
@@ -1307,8 +1316,7 @@ static ssize_t bonding_store_active_slave(struct device *d,
 						slave->dev->name);
 					bond_change_active_slave(bond,
 								 new_active);
-				}
-				else {
+				} else {
 					pr_info("%s: Could not set %s as"
 						" active slave; either %s is"
 						" down or the link is down.\n",
@@ -1344,14 +1352,9 @@ static ssize_t bonding_show_mii_status(struct device *d,
 				       struct device_attribute *attr,
 				       char *buf)
 {
-	struct slave *curr;
 	struct bonding *bond = to_bond(d);
 
-	read_lock(&bond->curr_slave_lock);
-	curr = bond->curr_active_slave;
-	read_unlock(&bond->curr_slave_lock);
-
-	return sprintf(buf, "%s\n", curr ? "up" : "down");
+	return sprintf(buf, "%s\n", bond->curr_active_slave ? "up" : "down");
 }
 static DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL);
 
@@ -1470,15 +1473,15 @@ static ssize_t bonding_show_queue_id(struct device *d,
 				     struct device_attribute *attr,
 				     char *buf)
 {
-	struct slave *slave;
-	int i, res = 0;
 	struct bonding *bond = to_bond(d);
+	struct slave *slave;
+	int res = 0;
 
 	if (!rtnl_trylock())
 		return restart_syscall();
 
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (res > (PAGE_SIZE - IFNAMSIZ - 6)) {
 			/* not enough space for another interface_name:queue_id pair */
 			if ((PAGE_SIZE - res) > 10)
@@ -1493,6 +1496,7 @@ static ssize_t bonding_show_queue_id(struct device *d,
 	if (res)
 		buf[res-1] = '\n'; /* eat the leftover space */
 	rtnl_unlock();
+
 	return res;
 }
 
@@ -1507,7 +1511,7 @@ static ssize_t bonding_store_queue_id(struct device *d,
 	struct slave *slave, *update_slave;
 	struct bonding *bond = to_bond(d);
 	u16 qid;
-	int i, ret = count;
+	int ret = count;
 	char *delim;
 	struct net_device *sdev = NULL;
 
@@ -1542,7 +1546,7 @@ static ssize_t bonding_store_queue_id(struct device *d,
 
 	/* Search for thes slave and check for duplicate qids */
 	update_slave = NULL;
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (sdev == slave->dev)
 			/*
 			 * We don't need to check the matching
@@ -1594,8 +1598,8 @@ static ssize_t bonding_store_slaves_active(struct device *d,
 					   struct device_attribute *attr,
 					   const char *buf, size_t count)
 {
-	int i, new_value, ret = count;
 	struct bonding *bond = to_bond(d);
+	int new_value, ret = count;
 	struct slave *slave;
 
 	if (sscanf(buf, "%d", &new_value) != 1) {
@@ -1618,7 +1622,7 @@ static ssize_t bonding_store_slaves_active(struct device *d,
 	}
 
 	read_lock(&bond->lock);
-	bond_for_each_slave(bond, slave, i) {
+	bond_for_each_slave(bond, slave) {
 		if (!bond_is_active_slave(slave)) {
 			if (new_value)
 				slave->inactive = 0;

drivers/net/bonding/bonding.h

@@ -71,6 +71,28 @@
 	set_fs(fs);			\
 	res; })
 
+/* slave list primitives */
+#define bond_to_slave(ptr) list_entry(ptr, struct slave, list)
+
+/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */
+#define bond_first_slave(bond) \
+	list_first_entry_or_null(&(bond)->slave_list, struct slave, list)
+#define bond_last_slave(bond) \
+	(list_empty(&(bond)->slave_list) ? NULL : \
+					   bond_to_slave((bond)->slave_list.prev))
+
+#define bond_is_first_slave(bond, pos) ((pos)->list.prev == &(bond)->slave_list)
+#define bond_is_last_slave(bond, pos) ((pos)->list.next == &(bond)->slave_list)
+
+/* Since bond_first/last_slave can return NULL, these can return NULL too */
+#define bond_next_slave(bond, pos) \
+	(bond_is_last_slave(bond, pos) ? bond_first_slave(bond) : \
+					 bond_to_slave((pos)->list.next))
+
+#define bond_prev_slave(bond, pos) \
+	(bond_is_first_slave(bond, pos) ? bond_last_slave(bond) : \
+					  bond_to_slave((pos)->list.prev))
+
 /**
  * bond_for_each_slave_from - iterate the slaves list from a starting point
  * @bond:	the bond holding this list.
@@ -80,37 +102,33 @@
  *
  * Caller must hold bond->lock
  */
-#define bond_for_each_slave_from(bond, pos, cnt, start)	\
-	for (cnt = 0, pos = start;				\
-	     cnt < (bond)->slave_cnt;				\
-             cnt++, pos = (pos)->next)
+#define bond_for_each_slave_from(bond, pos, cnt, start) \
+	for (cnt = 0, pos = start; pos && cnt < (bond)->slave_cnt; \
+	     cnt++, pos = bond_next_slave(bond, pos))
 
 /**
- * bond_for_each_slave_from_to - iterate the slaves list from start point to stop point
- * @bond:	the bond holding this list.
- * @pos:	current slave.
- * @cnt:	counter for number max of moves
- * @start:	start point.
- * @stop:	stop point.
+ * bond_for_each_slave - iterate over all slaves
+ * @bond:	the bond holding this list
+ * @pos:	current slave
  *
  * Caller must hold bond->lock
  */
-#define bond_for_each_slave_from_to(bond, pos, cnt, start, stop)	\
-	for (cnt = 0, pos = start;					\
-	     ((cnt < (bond)->slave_cnt) && (pos != (stop)->next));	\
-             cnt++, pos = (pos)->next)
+#define bond_for_each_slave(bond, pos) \
+	list_for_each_entry(pos, &(bond)->slave_list, list)
+
+/* Caller must have rcu_read_lock */
+#define bond_for_each_slave_rcu(bond, pos) \
+	list_for_each_entry_rcu(pos, &(bond)->slave_list, list)
 
 /**
- * bond_for_each_slave - iterate the slaves list from head
- * @bond:	the bond holding this list.
- * @pos:	current slave.
- * @cnt:	counter for max number of moves
+ * bond_for_each_slave_reverse - iterate in reverse from a given position
+ * @bond:	the bond holding this list
+ * @pos:	slave to continue from
  *
  * Caller must hold bond->lock
  */
-#define bond_for_each_slave(bond, pos, cnt)	\
-		bond_for_each_slave_from(bond, pos, cnt, (bond)->first_slave)
-
+#define bond_for_each_slave_continue_reverse(bond, pos) \
+	list_for_each_entry_continue_reverse(pos, &(bond)->slave_list, list)
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 extern atomic_t netpoll_block_tx;
@@ -167,15 +185,9 @@ struct bond_parm_tbl {
 
 #define BOND_MAX_MODENAME_LEN 20
 
-struct vlan_entry {
-	struct list_head vlan_list;
-	unsigned short vlan_id;
-};
-
 struct slave {
 	struct net_device *dev; /* first - useful for panic debug */
-	struct slave *next;
-	struct slave *prev;
+	struct list_head list;
 	struct bonding *bond; /* our master */
 	int    delay;
 	unsigned long jiffies;
@@ -215,7 +227,7 @@ struct slave {
  */
 struct bonding {
 	struct   net_device *dev; /* first - useful for panic debug */
-	struct   slave *first_slave;
+	struct   list_head slave_list;
 	struct   slave *curr_active_slave;
 	struct   slave *current_arp_slave;
 	struct   slave *primary_slave;
@@ -237,7 +249,6 @@ struct bonding {
 	struct   ad_bond_info ad_info;
 	struct   alb_bond_info alb_info;
 	struct   bond_params params;
-	struct   list_head vlan_list;
 	struct   workqueue_struct *wq;
 	struct   delayed_work mii_work;
 	struct   delayed_work arp_work;
@@ -250,11 +261,6 @@ struct bonding {
 #endif /* CONFIG_DEBUG_FS */
 };
 
-static inline bool bond_vlan_used(struct bonding *bond)
-{
-	return !list_empty(&bond->vlan_list);
-}
-
 #define bond_slave_get_rcu(dev) \
 	((struct slave *) rcu_dereference(dev->rx_handler_data))
 
@@ -270,13 +276,10 @@ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond,
 						  struct net_device *slave_dev)
 {
 	struct slave *slave = NULL;
-	int i;
 
-	bond_for_each_slave(bond, slave, i) {
-		if (slave->dev == slave_dev) {
+	bond_for_each_slave(bond, slave)
+		if (slave->dev == slave_dev)
 			return slave;
-		}
-	}
 
 	return NULL;
 }
@@ -416,10 +419,20 @@ static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be3
 	return addr;
 }
 
+static inline bool slave_can_tx(struct slave *slave)
+{
+	if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP &&
+	    bond_is_active_slave(slave))
+		return true;
+	else
+		return false;
+}
+
 struct bond_net;
 
 struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr);
 int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
+void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id);
 int bond_create(struct net *net, const char *name);
 int bond_create_sysfs(struct bond_net *net);
 void bond_destroy_sysfs(struct bond_net *net);
@@ -477,10 +490,9 @@ static inline void bond_destroy_proc_dir(struct bond_net *bn)
 static inline struct slave *bond_slave_has_mac(struct bonding *bond,
 					       const u8 *mac)
 {
-	int i = 0;
 	struct slave *tmp;
 
-	bond_for_each_slave(bond, tmp, i)
+	bond_for_each_slave(bond, tmp)
 		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
 			return tmp;
 

drivers/net/caif/caif_serial.c

@@ -347,7 +347,9 @@ static int ldisc_open(struct tty_struct *tty)
 	/* release devices to avoid name collision */
 	ser_release(NULL);
 
-	sprintf(name, "cf%s", tty->name);
+	result = snprintf(name, sizeof(name), "cf%s", tty->name);
+	if (result >= IFNAMSIZ)
+		return -EINVAL;
 	dev = alloc_netdev(sizeof(*ser), name, caifdev_setup);
 	if (!dev)
 		return -ENOMEM;

drivers/net/can/at91_can.c

@@ -1355,7 +1355,7 @@ static int at91_can_probe(struct platform_device *pdev)
 	if (at91_is_sam9263(priv))
 		dev->sysfs_groups[0] = &at91_sysfs_attr_group;
 
-	dev_set_drvdata(&pdev->dev, dev);
+	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	err = register_candev(dev);

drivers/net/can/c_can/c_can_platform.c

@@ -195,7 +195,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 		priv->raminit_ctrlreg = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(priv->raminit_ctrlreg) || priv->instance < 0)
+		if (IS_ERR(priv->raminit_ctrlreg) || (int)priv->instance < 0)
 			dev_info(&pdev->dev, "control memory is not used for raminit\n");
 		else
 			priv->raminit = c_can_hw_raminit;

drivers/net/can/flexcan.c

@@ -850,12 +850,17 @@ static int flexcan_open(struct net_device *dev)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
-	clk_prepare_enable(priv->clk_ipg);
-	clk_prepare_enable(priv->clk_per);
+	err = clk_prepare_enable(priv->clk_ipg);
+	if (err)
+		return err;
+
+	err = clk_prepare_enable(priv->clk_per);
+	if (err)
+		goto out_disable_ipg;
 
 	err = open_candev(dev);
 	if (err)
-		goto out;
+		goto out_disable_per;
 
 	err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
 	if (err)
@@ -875,8 +880,9 @@ static int flexcan_open(struct net_device *dev)
 
  out_close:
 	close_candev(dev);
- out:
+ out_disable_per:
 	clk_disable_unprepare(priv->clk_per);
+ out_disable_ipg:
 	clk_disable_unprepare(priv->clk_ipg);
 
 	return err;
@@ -933,8 +939,13 @@ static int register_flexcandev(struct net_device *dev)
 	struct flexcan_regs __iomem *regs = priv->base;
 	u32 reg, err;
 
-	clk_prepare_enable(priv->clk_ipg);
-	clk_prepare_enable(priv->clk_per);
+	err = clk_prepare_enable(priv->clk_ipg);
+	if (err)
+		return err;
+
+	err = clk_prepare_enable(priv->clk_per);
+	if (err)
+		goto out_disable_ipg;
 
 	/* select "bus clock", chip must be disabled */
 	flexcan_chip_disable(priv);
@@ -959,15 +970,16 @@ static int register_flexcandev(struct net_device *dev)
 	if (!(reg & FLEXCAN_MCR_FEN)) {
 		netdev_err(dev, "Could not enable RX FIFO, unsupported core\n");
 		err = -ENODEV;
-		goto out;
+		goto out_disable_per;
 	}
 
 	err = register_candev(dev);
 
- out:
+ out_disable_per:
 	/* disable core and turn off clocks */
 	flexcan_chip_disable(priv);
 	clk_disable_unprepare(priv->clk_per);
+ out_disable_ipg:
 	clk_disable_unprepare(priv->clk_ipg);
 
 	return err;
@@ -1001,7 +1013,6 @@ static int flexcan_probe(struct platform_device *pdev)
 	struct resource *mem;
 	struct clk *clk_ipg = NULL, *clk_per = NULL;
 	void __iomem *base;
-	resource_size_t mem_size;
 	int err, irq;
 	u32 clock_freq = 0;
 
@@ -1013,43 +1024,25 @@ static int flexcan_probe(struct platform_device *pdev)
 		clk_ipg = devm_clk_get(&pdev->dev, "ipg");
 		if (IS_ERR(clk_ipg)) {
 			dev_err(&pdev->dev, "no ipg clock defined\n");
-			err = PTR_ERR(clk_ipg);
-			goto failed_clock;
+			return PTR_ERR(clk_ipg);
 		}
 		clock_freq = clk_get_rate(clk_ipg);
 
 		clk_per = devm_clk_get(&pdev->dev, "per");
 		if (IS_ERR(clk_per)) {
 			dev_err(&pdev->dev, "no per clock defined\n");
-			err = PTR_ERR(clk_per);
-			goto failed_clock;
+			return PTR_ERR(clk_per);
 		}
 	}
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if (!mem || irq <= 0) {
-		err = -ENODEV;
-		goto failed_get;
-	}
+	if (irq <= 0)
+		return -ENODEV;
 
-	mem_size = resource_size(mem);
-	if (!request_mem_region(mem->start, mem_size, pdev->name)) {
-		err = -EBUSY;
-		goto failed_get;
-	}
-
-	base = ioremap(mem->start, mem_size);
-	if (!base) {
-		err = -ENOMEM;
-		goto failed_map;
-	}
-
-	dev = alloc_candev(sizeof(struct flexcan_priv), 1);
-	if (!dev) {
-		err = -ENOMEM;
-		goto failed_alloc;
-	}
+	base = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	of_id = of_match_device(flexcan_of_match, &pdev->dev);
 	if (of_id) {
@@ -1058,10 +1051,13 @@ static int flexcan_probe(struct platform_device *pdev)
 		devtype_data = (struct flexcan_devtype_data *)
 			pdev->id_entry->driver_data;
 	} else {
-		err = -ENODEV;
-		goto failed_devtype;
+		return -ENODEV;
 	}
 
+	dev = alloc_candev(sizeof(struct flexcan_priv), 1);
+	if (!dev)
+		return -ENOMEM;
+
 	dev->netdev_ops = &flexcan_netdev_ops;
 	dev->irq = irq;
 	dev->flags |= IFF_ECHO;
@@ -1087,7 +1083,7 @@ static int flexcan_probe(struct platform_device *pdev)
 
 	netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT);
 
-	dev_set_drvdata(&pdev->dev, dev);
+	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	err = register_flexcandev(dev);
@@ -1104,28 +1100,15 @@ static int flexcan_probe(struct platform_device *pdev)
 	return 0;
 
  failed_register:
- failed_devtype:
 	free_candev(dev);
- failed_alloc:
-	iounmap(base);
- failed_map:
-	release_mem_region(mem->start, mem_size);
- failed_get:
- failed_clock:
 	return err;
 }
 
 static int flexcan_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
-	struct flexcan_priv *priv = netdev_priv(dev);
-	struct resource *mem;
 
 	unregister_flexcandev(dev);
-	iounmap(priv->base);
-
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(mem->start, resource_size(mem));
 
 	free_candev(dev);
 

drivers/net/can/mcp251x.c

@@ -37,9 +37,6 @@
  *
  * static struct mcp251x_platform_data mcp251x_info = {
  *         .oscillator_frequency = 8000000,
- *         .board_specific_setup = &mcp251x_setup,
- *         .power_enable = mcp251x_power_enable,
- *         .transceiver_enable = NULL,
  * };
  *
  * static struct spi_board_info spi_board_info[] = {
@@ -76,6 +73,7 @@
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
 #include <linux/uaccess.h>
+#include <linux/regulator/consumer.h>
 
 /* SPI interface instruction set */
 #define INSTRUCTION_WRITE	0x02
@@ -264,6 +262,8 @@ struct mcp251x_priv {
 #define AFTER_SUSPEND_POWER 4
 #define AFTER_SUSPEND_RESTART 8
 	int restart_tx;
+	struct regulator *power;
+	struct regulator *transceiver;
 };
 
 #define MCP251X_IS(_model) \
@@ -667,16 +667,25 @@ static int mcp251x_hw_probe(struct spi_device *spi)
 	return (st1 == 0x80 && st2 == 0x07) ? 1 : 0;
 }
 
+static int mcp251x_power_enable(struct regulator *reg, int enable)
+{
+	if (IS_ERR(reg))
+		return 0;
+
+	if (enable)
+		return regulator_enable(reg);
+	else
+		return regulator_disable(reg);
+}
+
 static void mcp251x_open_clean(struct net_device *net)
 {
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
-	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
 
 	free_irq(spi->irq, priv);
 	mcp251x_hw_sleep(spi);
-	if (pdata->transceiver_enable)
-		pdata->transceiver_enable(0);
+	mcp251x_power_enable(priv->transceiver, 0);
 	close_candev(net);
 }
 
@@ -684,7 +693,6 @@ static int mcp251x_stop(struct net_device *net)
 {
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
-	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
 
 	close_candev(net);
 
@@ -704,8 +712,7 @@ static int mcp251x_stop(struct net_device *net)
 
 	mcp251x_hw_sleep(spi);
 
-	if (pdata->transceiver_enable)
-		pdata->transceiver_enable(0);
+	mcp251x_power_enable(priv->transceiver, 0);
 
 	priv->can.state = CAN_STATE_STOPPED;
 
@@ -928,8 +935,7 @@ static int mcp251x_open(struct net_device *net)
 {
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
-	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
-	unsigned long flags;
+	unsigned long flags = IRQF_ONESHOT | IRQF_TRIGGER_FALLING;
 	int ret;
 
 	ret = open_candev(net);
@@ -939,25 +945,17 @@ static int mcp251x_open(struct net_device *net)
 	}
 
 	mutex_lock(&priv->mcp_lock);
-	if (pdata->transceiver_enable)
-		pdata->transceiver_enable(1);
+	mcp251x_power_enable(priv->transceiver, 1);
 
 	priv->force_quit = 0;
 	priv->tx_skb = NULL;
 	priv->tx_len = 0;
 
-	flags = IRQF_ONESHOT;
-	if (pdata->irq_flags)
-		flags |= pdata->irq_flags;
-	else
-		flags |= IRQF_TRIGGER_FALLING;
-
 	ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist,
 				   flags, DEVICE_NAME, priv);
 	if (ret) {
 		dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
-		if (pdata->transceiver_enable)
-			pdata->transceiver_enable(0);
+		mcp251x_power_enable(priv->transceiver, 0);
 		close_candev(net);
 		goto open_unlock;
 	}
@@ -1026,6 +1024,19 @@ static int mcp251x_can_probe(struct spi_device *spi)
 		CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY;
 	priv->model = spi_get_device_id(spi)->driver_data;
 	priv->net = net;
+
+	priv->power = devm_regulator_get(&spi->dev, "vdd");
+	priv->transceiver = devm_regulator_get(&spi->dev, "xceiver");
+	if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
+	    (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
+		ret = -EPROBE_DEFER;
+		goto error_power;
+	}
+
+	ret = mcp251x_power_enable(priv->power, 1);
+	if (ret)
+		goto error_power;
+
 	spi_set_drvdata(spi, priv);
 
 	priv->spi = spi;
@@ -1068,30 +1079,24 @@ static int mcp251x_can_probe(struct spi_device *spi)
 		}
 	}
 
-	if (pdata->power_enable)
-		pdata->power_enable(1);
-
-	/* Call out to platform specific setup */
-	if (pdata->board_specific_setup)
-		pdata->board_specific_setup(spi);
-
 	SET_NETDEV_DEV(net, &spi->dev);
 
 	/* Configure the SPI bus */
-	spi->mode = SPI_MODE_0;
+	spi->mode = spi->mode ? : SPI_MODE_0;
+	if (mcp251x_is_2510(spi))
+		spi->max_speed_hz = spi->max_speed_hz ? : 5 * 1000 * 1000;
+	else
+		spi->max_speed_hz = spi->max_speed_hz ? : 10 * 1000 * 1000;
 	spi->bits_per_word = 8;
 	spi_setup(spi);
 
 	/* Here is OK to not lock the MCP, no one knows about it yet */
 	if (!mcp251x_hw_probe(spi)) {
-		dev_info(&spi->dev, "Probe failed\n");
+		ret = -ENODEV;
 		goto error_probe;
 	}
 	mcp251x_hw_sleep(spi);
 
-	if (pdata->transceiver_enable)
-		pdata->transceiver_enable(0);
-
 	ret = register_candev(net);
 	if (ret)
 		goto error_probe;
@@ -1109,13 +1114,13 @@ error_rx_buf:
 	if (!mcp251x_enable_dma)
 		kfree(priv->spi_tx_buf);
 error_tx_buf:
-	free_candev(net);
 	if (mcp251x_enable_dma)
 		dma_free_coherent(&spi->dev, PAGE_SIZE,
 				  priv->spi_tx_buf, priv->spi_tx_dma);
+	mcp251x_power_enable(priv->power, 0);
+error_power:
+	free_candev(net);
 error_alloc:
-	if (pdata->power_enable)
-		pdata->power_enable(0);
 	dev_err(&spi->dev, "probe failed\n");
 error_out:
 	return ret;
@@ -1123,12 +1128,10 @@ error_out:
 
 static int mcp251x_can_remove(struct spi_device *spi)
 {
-	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
 	struct net_device *net = priv->net;
 
 	unregister_candev(net);
-	free_candev(net);
 
 	if (mcp251x_enable_dma) {
 		dma_free_coherent(&spi->dev, PAGE_SIZE,
@@ -1138,8 +1141,9 @@ static int mcp251x_can_remove(struct spi_device *spi)
 		kfree(priv->spi_rx_buf);
 	}
 
-	if (pdata->power_enable)
-		pdata->power_enable(0);
+	mcp251x_power_enable(priv->power, 0);
+
+	free_candev(net);
 
 	return 0;
 }
@@ -1149,7 +1153,6 @@ static int mcp251x_can_remove(struct spi_device *spi)
 static int mcp251x_can_suspend(struct device *dev)
 {
 	struct spi_device *spi = to_spi_device(dev);
-	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
 	struct net_device *net = priv->net;
 
@@ -1163,15 +1166,14 @@ static int mcp251x_can_suspend(struct device *dev)
 		netif_device_detach(net);
 
 		mcp251x_hw_sleep(spi);
-		if (pdata->transceiver_enable)
-			pdata->transceiver_enable(0);
+		mcp251x_power_enable(priv->transceiver, 0);
 		priv->after_suspend = AFTER_SUSPEND_UP;
 	} else {
 		priv->after_suspend = AFTER_SUSPEND_DOWN;
 	}
 
-	if (pdata->power_enable) {
-		pdata->power_enable(0);
+	if (!IS_ERR(priv->power)) {
+		regulator_disable(priv->power);
 		priv->after_suspend |= AFTER_SUSPEND_POWER;
 	}
 
@@ -1181,16 +1183,14 @@ static int mcp251x_can_suspend(struct device *dev)
 static int mcp251x_can_resume(struct device *dev)
 {
 	struct spi_device *spi = to_spi_device(dev);
-	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
 
 	if (priv->after_suspend & AFTER_SUSPEND_POWER) {
-		pdata->power_enable(1);
+		mcp251x_power_enable(priv->power, 1);
 		queue_work(priv->wq, &priv->restart_work);
 	} else {
 		if (priv->after_suspend & AFTER_SUSPEND_UP) {
-			if (pdata->transceiver_enable)
-				pdata->transceiver_enable(1);
+			mcp251x_power_enable(priv->transceiver, 1);
 			queue_work(priv->wq, &priv->restart_work);
 		} else {
 			priv->after_suspend = 0;

drivers/net/can/mscan/mpc5xxx_can.c

@@ -40,6 +40,7 @@ struct mpc5xxx_can_data {
 	unsigned int type;
 	u32 (*get_clock)(struct platform_device *ofdev, const char *clock_name,
 			 int *mscan_clksrc);
+	void (*put_clock)(struct platform_device *ofdev);
 };
 
 #ifdef CONFIG_PPC_MPC52xx
@@ -148,7 +149,10 @@ static u32 mpc512x_can_get_clock(struct platform_device *ofdev,
 		goto exit_put;
 	}
 
-	/* Determine the MSCAN device index from the physical address */
+	/* Determine the MSCAN device index from the peripheral's
+	 * physical address. Register address offsets against the
+	 * IMMR base are:  0x1300, 0x1380, 0x2300, 0x2380
+	 */
 	pval = of_get_property(ofdev->dev.of_node, "reg", &plen);
 	BUG_ON(!pval || plen < sizeof(*pval));
 	clockidx = (*pval & 0x80) ? 1 : 0;
@@ -177,7 +181,7 @@ static u32 mpc512x_can_get_clock(struct platform_device *ofdev,
 			clockdiv = 1;
 
 		if (!clock_name || !strcmp(clock_name, "sys")) {
-			sys_clk = clk_get(&ofdev->dev, "sys_clk");
+			sys_clk = devm_clk_get(&ofdev->dev, "sys_clk");
 			if (IS_ERR(sys_clk)) {
 				dev_err(&ofdev->dev, "couldn't get sys_clk\n");
 				goto exit_unmap;
@@ -200,7 +204,7 @@ static u32 mpc512x_can_get_clock(struct platform_device *ofdev,
 		}
 
 		if (clocksrc < 0) {
-			ref_clk = clk_get(&ofdev->dev, "ref_clk");
+			ref_clk = devm_clk_get(&ofdev->dev, "ref_clk");
 			if (IS_ERR(ref_clk)) {
 				dev_err(&ofdev->dev, "couldn't get ref_clk\n");
 				goto exit_unmap;
@@ -277,6 +281,8 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 	dev = alloc_mscandev();
 	if (!dev)
 		goto exit_dispose_irq;
+	platform_set_drvdata(ofdev, dev);
+	SET_NETDEV_DEV(dev, &ofdev->dev);
 
 	priv = netdev_priv(dev);
 	priv->reg_base = base;
@@ -293,8 +299,6 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 		goto exit_free_mscan;
 	}
 
-	SET_NETDEV_DEV(dev, &ofdev->dev);
-
 	err = register_mscandev(dev, mscan_clksrc);
 	if (err) {
 		dev_err(&ofdev->dev, "registering %s failed (err=%d)\n",
@@ -302,8 +306,6 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 		goto exit_free_mscan;
 	}
 
-	platform_set_drvdata(ofdev, dev);
-
 	dev_info(&ofdev->dev, "MSCAN at 0x%p, irq %d, clock %d Hz\n",
 		 priv->reg_base, dev->irq, priv->can.clock.freq);
 
@@ -321,10 +323,17 @@ exit_unmap_mem:
 
 static int mpc5xxx_can_remove(struct platform_device *ofdev)
 {
+	const struct of_device_id *match;
+	const struct mpc5xxx_can_data *data;
 	struct net_device *dev = platform_get_drvdata(ofdev);
 	struct mscan_priv *priv = netdev_priv(dev);
 
+	match = of_match_device(mpc5xxx_can_table, &ofdev->dev);
+	data = match ? match->data : NULL;
+
 	unregister_mscandev(dev);
+	if (data && data->put_clock)
+		data->put_clock(ofdev);
 	iounmap(priv->reg_base);
 	irq_dispose_mapping(dev->irq);
 	free_candev(dev);

drivers/net/can/mscan/mscan.c

@@ -573,10 +573,21 @@ static int mscan_open(struct net_device *dev)
 	struct mscan_priv *priv = netdev_priv(dev);
 	struct mscan_regs __iomem *regs = priv->reg_base;
 
+	if (priv->clk_ipg) {
+		ret = clk_prepare_enable(priv->clk_ipg);
+		if (ret)
+			goto exit_retcode;
+	}
+	if (priv->clk_can) {
+		ret = clk_prepare_enable(priv->clk_can);
+		if (ret)
+			goto exit_dis_ipg_clock;
+	}
+
 	/* common open */
 	ret = open_candev(dev);
 	if (ret)
-		return ret;
+		goto exit_dis_can_clock;
 
 	napi_enable(&priv->napi);
 
@@ -604,6 +615,13 @@ exit_free_irq:
 exit_napi_disable:
 	napi_disable(&priv->napi);
 	close_candev(dev);
+exit_dis_can_clock:
+	if (priv->clk_can)
+		clk_disable_unprepare(priv->clk_can);
+exit_dis_ipg_clock:
+	if (priv->clk_ipg)
+		clk_disable_unprepare(priv->clk_ipg);
+exit_retcode:
 	return ret;
 }
 
@@ -621,6 +639,11 @@ static int mscan_close(struct net_device *dev)
 	close_candev(dev);
 	free_irq(dev->irq, dev);
 
+	if (priv->clk_can)
+		clk_disable_unprepare(priv->clk_can);
+	if (priv->clk_ipg)
+		clk_disable_unprepare(priv->clk_ipg);
+
 	return 0;
 }
 

drivers/net/can/mscan/mscan.h

@@ -21,6 +21,7 @@
 #ifndef __MSCAN_H__
 #define __MSCAN_H__
 
+#include <linux/clk.h>
 #include <linux/types.h>
 
 /* MSCAN control register 0 (CANCTL0) bits */
@@ -283,6 +284,8 @@ struct mscan_priv {
 	unsigned int type; 	/* MSCAN type variants */
 	unsigned long flags;
 	void __iomem *reg_base;	/* ioremap'ed address to registers */
+	struct clk *clk_ipg;	/* clock for registers */
+	struct clk *clk_can;	/* clock for bitrates */
 	u8 shadow_statflg;
 	u8 shadow_canrier;
 	u8 cur_pri;

drivers/net/ethernet/8390/Kconfig

@@ -148,7 +148,7 @@ config PCMCIA_PCNET
 
 config NE_H8300
 	tristate "NE2000 compatible support for H8/300"
-	depends on H8300
+	depends on H8300H_AKI3068NET || H8300H_H8MAX
 	---help---
 	  Say Y here if you want to use the NE2000 compatible
 	  controller on the Renesas H8/300 processor.

drivers/net/ethernet/8390/ax88796.c

@@ -707,7 +707,7 @@ static int ax_init_dev(struct net_device *dev)
 
 #ifdef CONFIG_AX88796_93CX6
 	if (ax->plat->flags & AXFLG_HAS_93CX6) {
-		unsigned char mac_addr[6];
+		unsigned char mac_addr[ETH_ALEN];
 		struct eeprom_93cx6 eeprom;
 
 		eeprom.data = ei_local;
@@ -719,7 +719,7 @@ static int ax_init_dev(struct net_device *dev)
 				       (__le16 __force *)mac_addr,
 				       sizeof(mac_addr) >> 1);
 
-		memcpy(dev->dev_addr, mac_addr, 6);
+		memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
 	}
 #endif
 	if (ax->plat->wordlength == 2) {
@@ -840,7 +840,7 @@ static int ax_probe(struct platform_device *pdev)
 	ei_local = netdev_priv(dev);
 	ax = to_ax_dev(dev);
 
-	ax->plat = pdev->dev.platform_data;
+	ax->plat = dev_get_platdata(&pdev->dev);
 	platform_set_drvdata(pdev, dev);
 
 	ei_local->rxcr_base = ax->plat->rcr_val;

drivers/net/ethernet/Kconfig

@@ -90,6 +90,7 @@ source "drivers/net/ethernet/marvell/Kconfig"
 source "drivers/net/ethernet/mellanox/Kconfig"
 source "drivers/net/ethernet/micrel/Kconfig"
 source "drivers/net/ethernet/microchip/Kconfig"
+source "drivers/net/ethernet/moxa/Kconfig"
 source "drivers/net/ethernet/myricom/Kconfig"
 
 config FEALNX

drivers/net/ethernet/Makefile

@@ -42,6 +42,7 @@ obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/
 obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/
 obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/
 obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/
+obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/
 obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/
 obj-$(CONFIG_FEALNX) += fealnx.o
 obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/

drivers/net/ethernet/adi/bfin_mac.c

@@ -1647,12 +1647,12 @@ static int bfin_mac_probe(struct platform_device *pdev)
 
 	setup_mac_addr(ndev->dev_addr);
 
-	if (!pdev->dev.platform_data) {
+	if (!dev_get_platdata(&pdev->dev)) {
 		dev_err(&pdev->dev, "Cannot get platform device bfin_mii_bus!\n");
 		rc = -ENODEV;
 		goto out_err_probe_mac;
 	}
-	pd = pdev->dev.platform_data;
+	pd = dev_get_platdata(&pdev->dev);
 	lp->mii_bus = platform_get_drvdata(pd);
 	if (!lp->mii_bus) {
 		dev_err(&pdev->dev, "Cannot get mii_bus!\n");
@@ -1660,7 +1660,7 @@ static int bfin_mac_probe(struct platform_device *pdev)
 		goto out_err_probe_mac;
 	}
 	lp->mii_bus->priv = ndev;
-	mii_bus_data = pd->dev.platform_data;
+	mii_bus_data = dev_get_platdata(&pd->dev);
 
 	rc = mii_probe(ndev, mii_bus_data->phy_mode);
 	if (rc) {

drivers/net/ethernet/aeroflex/greth.c

@@ -1464,18 +1464,18 @@ static int greth_of_probe(struct platform_device *ofdev)
 	}
 
 	/* Allocate TX descriptor ring in coherent memory */
-	greth->tx_bd_base = dma_alloc_coherent(greth->dev, 1024,
-					       &greth->tx_bd_base_phys,
-					       GFP_KERNEL | __GFP_ZERO);
+	greth->tx_bd_base = dma_zalloc_coherent(greth->dev, 1024,
+						&greth->tx_bd_base_phys,
+						GFP_KERNEL);
 	if (!greth->tx_bd_base) {
 		err = -ENOMEM;
 		goto error3;
 	}
 
 	/* Allocate RX descriptor ring in coherent memory */
-	greth->rx_bd_base = dma_alloc_coherent(greth->dev, 1024,
-					       &greth->rx_bd_base_phys,
-					       GFP_KERNEL | __GFP_ZERO);
+	greth->rx_bd_base = dma_zalloc_coherent(greth->dev, 1024,
+						&greth->rx_bd_base_phys,
+						GFP_KERNEL);
 	if (!greth->rx_bd_base) {
 		err = -ENOMEM;
 		goto error4;

drivers/net/ethernet/amd/au1000_eth.c

@@ -1131,7 +1131,7 @@ static int au1000_probe(struct platform_device *pdev)
 	writel(0, aup->enable);
 	aup->mac_enabled = 0;
 
-	pd = pdev->dev.platform_data;
+	pd = dev_get_platdata(&pdev->dev);
 	if (!pd) {
 		dev_info(&pdev->dev, "no platform_data passed,"
 					" PHY search on MAC0\n");

drivers/net/ethernet/amd/pcnet32.c

@@ -1521,7 +1521,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 	char *chipname;
 	struct net_device *dev;
 	const struct pcnet32_access *a = NULL;
-	u8 promaddr[6];
+	u8 promaddr[ETH_ALEN];
 	int ret = -ENODEV;
 
 	/* reset the chip */
@@ -1665,10 +1665,10 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 	}
 
 	/* read PROM address and compare with CSR address */
-	for (i = 0; i < 6; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		promaddr[i] = inb(ioaddr + i);
 
-	if (memcmp(promaddr, dev->dev_addr, 6) ||
+	if (memcmp(promaddr, dev->dev_addr, ETH_ALEN) ||
 	    !is_valid_ether_addr(dev->dev_addr)) {
 		if (is_valid_ether_addr(promaddr)) {
 			if (pcnet32_debug & NETIF_MSG_PROBE) {

drivers/net/ethernet/arc/emac_main.c

@@ -149,8 +149,6 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 		struct sk_buff *skb = tx_buff->skb;
 		unsigned int info = le32_to_cpu(txbd->info);
 
-		*txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM;
-
 		if ((info & FOR_EMAC) || !txbd->data)
 			break;
 
@@ -180,6 +178,8 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 		txbd->data = 0;
 		txbd->info = 0;
 
+		*txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM;
+
 		if (netif_queue_stopped(ndev))
 			netif_wake_queue(ndev);
 	}

drivers/net/ethernet/broadcom/Kconfig

@@ -130,7 +130,7 @@ config BNX2X_SRIOV
 
 config BGMAC
 	tristate "BCMA bus GBit core support"
-	depends on BCMA_HOST_SOC && HAS_DMA
+	depends on BCMA_HOST_SOC && HAS_DMA && BCM47XX
 	select PHYLIB
 	---help---
 	  This driver supports GBit MAC and BCM4706 GBit MAC cores on BCMA bus.

drivers/net/ethernet/broadcom/bcm63xx_enet.c

@@ -948,8 +948,7 @@ static int bcm_enet_open(struct net_device *dev)
 
 	/* allocate rx dma ring */
 	size = priv->rx_ring_size * sizeof(struct bcm_enet_desc);
-	p = dma_alloc_coherent(kdev, size, &priv->rx_desc_dma,
-			       GFP_KERNEL | __GFP_ZERO);
+	p = dma_zalloc_coherent(kdev, size, &priv->rx_desc_dma, GFP_KERNEL);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out_freeirq_tx;
@@ -960,8 +959,7 @@ static int bcm_enet_open(struct net_device *dev)
 
 	/* allocate tx dma ring */
 	size = priv->tx_ring_size * sizeof(struct bcm_enet_desc);
-	p = dma_alloc_coherent(kdev, size, &priv->tx_desc_dma,
-			       GFP_KERNEL | __GFP_ZERO);
+	p = dma_zalloc_coherent(kdev, size, &priv->tx_desc_dma, GFP_KERNEL);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out_free_rx_ring;
@@ -1747,11 +1745,10 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	if (!bcm_enet_shared_base[0])
 		return -ENODEV;
 
-	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	res_irq_rx = platform_get_resource(pdev, IORESOURCE_IRQ, 1);
 	res_irq_tx = platform_get_resource(pdev, IORESOURCE_IRQ, 2);
-	if (!res_mem || !res_irq || !res_irq_rx || !res_irq_tx)
+	if (!res_irq || !res_irq_rx || !res_irq_tx)
 		return -ENODEV;
 
 	ret = 0;
@@ -1767,9 +1764,10 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	if (ret)
 		goto out;
 
-	priv->base = devm_request_and_ioremap(&pdev->dev, res_mem);
-	if (priv->base == NULL) {
-		ret = -ENOMEM;
+	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, res_mem);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
 		goto out;
 	}
 
@@ -1800,7 +1798,7 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	priv->rx_ring_size = BCMENET_DEF_RX_DESC;
 	priv->tx_ring_size = BCMENET_DEF_TX_DESC;
 
-	pd = pdev->dev.platform_data;
+	pd = dev_get_platdata(&pdev->dev);
 	if (pd) {
 		memcpy(dev->dev_addr, pd->mac_addr, ETH_ALEN);
 		priv->has_phy = pd->has_phy;
@@ -1964,7 +1962,7 @@ static int bcm_enet_remove(struct platform_device *pdev)
 	} else {
 		struct bcm63xx_enet_platform_data *pd;
 
-		pd = pdev->dev.platform_data;
+		pd = dev_get_platdata(&pdev->dev);
 		if (pd && pd->mii_config)
 			pd->mii_config(dev, 0, bcm_enet_mdio_read_mii,
 				       bcm_enet_mdio_write_mii);
@@ -2742,7 +2740,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	priv->tx_ring_size = BCMENET_DEF_TX_DESC;
 	priv->dma_maxburst = BCMENETSW_DMA_MAXBURST;
 
-	pd = pdev->dev.platform_data;
+	pd = dev_get_platdata(&pdev->dev);
 	if (pd) {
 		memcpy(dev->dev_addr, pd->mac_addr, ETH_ALEN);
 		memcpy(priv->used_ports, pd->used_ports,
@@ -2836,7 +2834,6 @@ static int bcm_enetsw_remove(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	release_mem_region(res->start, resource_size(res));
 
-	platform_set_drvdata(pdev, NULL);
 	free_netdev(dev);
 	return 0;
 }

drivers/net/ethernet/broadcom/bnx2.c

@@ -1,6 +1,6 @@
 /* bnx2.c: Broadcom NX2 network driver.
  *
- * Copyright (c) 2004-2011 Broadcom Corporation
+ * Copyright (c) 2004-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -58,8 +58,8 @@
 #include "bnx2_fw.h"
 
 #define DRV_MODULE_NAME		"bnx2"
-#define DRV_MODULE_VERSION	"2.2.3"
-#define DRV_MODULE_RELDATE	"June 27, 2012"
+#define DRV_MODULE_VERSION	"2.2.4"
+#define DRV_MODULE_RELDATE	"Aug 05, 2013"
 #define FW_MIPS_FILE_06		"bnx2/bnx2-mips-06-6.2.3.fw"
 #define FW_RV2P_FILE_06		"bnx2/bnx2-rv2p-06-6.0.15.fw"
 #define FW_MIPS_FILE_09		"bnx2/bnx2-mips-09-6.2.1b.fw"
@@ -853,9 +853,8 @@ bnx2_alloc_mem(struct bnx2 *bp)
 	bp->status_stats_size = status_blk_size +
 				sizeof(struct statistics_block);
 
-	status_blk = dma_alloc_coherent(&bp->pdev->dev, bp->status_stats_size,
-					&bp->status_blk_mapping,
-					GFP_KERNEL | __GFP_ZERO);
+	status_blk = dma_zalloc_coherent(&bp->pdev->dev, bp->status_stats_size,
+					 &bp->status_blk_mapping, GFP_KERNEL);
 	if (status_blk == NULL)
 		goto alloc_mem_err;
 
@@ -3908,136 +3907,121 @@ init_cpu_err:
 	return rc;
 }
 
-static int
-bnx2_set_power_state(struct bnx2 *bp, pci_power_t state)
+static void
+bnx2_setup_wol(struct bnx2 *bp)
 {
-	u16 pmcsr;
+	int i;
+	u32 val, wol_msg;
 
-	pci_read_config_word(bp->pdev, bp->pm_cap + PCI_PM_CTRL, &pmcsr);
+	if (bp->wol) {
+		u32 advertising;
+		u8 autoneg;
 
-	switch (state) {
-	case PCI_D0: {
-		u32 val;
+		autoneg = bp->autoneg;
+		advertising = bp->advertising;
 
-		pci_write_config_word(bp->pdev, bp->pm_cap + PCI_PM_CTRL,
-			(pmcsr & ~PCI_PM_CTRL_STATE_MASK) |
-			PCI_PM_CTRL_PME_STATUS);
+		if (bp->phy_port == PORT_TP) {
+			bp->autoneg = AUTONEG_SPEED;
+			bp->advertising = ADVERTISED_10baseT_Half |
+				ADVERTISED_10baseT_Full |
+				ADVERTISED_100baseT_Half |
+				ADVERTISED_100baseT_Full |
+				ADVERTISED_Autoneg;
+		}
 
-		if (pmcsr & PCI_PM_CTRL_STATE_MASK)
-			/* delay required during transition out of D3hot */
-			msleep(20);
+		spin_lock_bh(&bp->phy_lock);
+		bnx2_setup_phy(bp, bp->phy_port);
+		spin_unlock_bh(&bp->phy_lock);
 
-		val = BNX2_RD(bp, BNX2_EMAC_MODE);
-		val |= BNX2_EMAC_MODE_MPKT_RCVD | BNX2_EMAC_MODE_ACPI_RCVD;
-		val &= ~BNX2_EMAC_MODE_MPKT;
-		BNX2_WR(bp, BNX2_EMAC_MODE, val);
+		bp->autoneg = autoneg;
+		bp->advertising = advertising;
 
-		val = BNX2_RD(bp, BNX2_RPM_CONFIG);
-		val &= ~BNX2_RPM_CONFIG_ACPI_ENA;
-		BNX2_WR(bp, BNX2_RPM_CONFIG, val);
-		break;
-	}
-	case PCI_D3hot: {
-		int i;
-		u32 val, wol_msg;
-
-		if (bp->wol) {
-			u32 advertising;
-			u8 autoneg;
-
-			autoneg = bp->autoneg;
-			advertising = bp->advertising;
-
-			if (bp->phy_port == PORT_TP) {
-				bp->autoneg = AUTONEG_SPEED;
-				bp->advertising = ADVERTISED_10baseT_Half |
-					ADVERTISED_10baseT_Full |
-					ADVERTISED_100baseT_Half |
-					ADVERTISED_100baseT_Full |
-					ADVERTISED_Autoneg;
-			}
+		bnx2_set_mac_addr(bp, bp->dev->dev_addr, 0);
 
-			spin_lock_bh(&bp->phy_lock);
-			bnx2_setup_phy(bp, bp->phy_port);
-			spin_unlock_bh(&bp->phy_lock);
+		val = BNX2_RD(bp, BNX2_EMAC_MODE);
 
-			bp->autoneg = autoneg;
-			bp->advertising = advertising;
+		/* Enable port mode. */
+		val &= ~BNX2_EMAC_MODE_PORT;
+		val |= BNX2_EMAC_MODE_MPKT_RCVD |
+		       BNX2_EMAC_MODE_ACPI_RCVD |
+		       BNX2_EMAC_MODE_MPKT;
+		if (bp->phy_port == PORT_TP) {
+			val |= BNX2_EMAC_MODE_PORT_MII;
+		} else {
+			val |= BNX2_EMAC_MODE_PORT_GMII;
+			if (bp->line_speed == SPEED_2500)
+				val |= BNX2_EMAC_MODE_25G_MODE;
+		}
 
-			bnx2_set_mac_addr(bp, bp->dev->dev_addr, 0);
+		BNX2_WR(bp, BNX2_EMAC_MODE, val);
 
-			val = BNX2_RD(bp, BNX2_EMAC_MODE);
+		/* receive all multicast */
+		for (i = 0; i < NUM_MC_HASH_REGISTERS; i++) {
+			BNX2_WR(bp, BNX2_EMAC_MULTICAST_HASH0 + (i * 4),
+				0xffffffff);
+		}
+		BNX2_WR(bp, BNX2_EMAC_RX_MODE, BNX2_EMAC_RX_MODE_SORT_MODE);
 
-			/* Enable port mode. */
-			val &= ~BNX2_EMAC_MODE_PORT;
-			val |= BNX2_EMAC_MODE_MPKT_RCVD |
-			       BNX2_EMAC_MODE_ACPI_RCVD |
-			       BNX2_EMAC_MODE_MPKT;
-			if (bp->phy_port == PORT_TP)
-				val |= BNX2_EMAC_MODE_PORT_MII;
-			else {
-				val |= BNX2_EMAC_MODE_PORT_GMII;
-				if (bp->line_speed == SPEED_2500)
-					val |= BNX2_EMAC_MODE_25G_MODE;
-			}
+		val = 1 | BNX2_RPM_SORT_USER0_BC_EN | BNX2_RPM_SORT_USER0_MC_EN;
+		BNX2_WR(bp, BNX2_RPM_SORT_USER0, 0x0);
+		BNX2_WR(bp, BNX2_RPM_SORT_USER0, val);
+		BNX2_WR(bp, BNX2_RPM_SORT_USER0, val | BNX2_RPM_SORT_USER0_ENA);
 
-			BNX2_WR(bp, BNX2_EMAC_MODE, val);
+		/* Need to enable EMAC and RPM for WOL. */
+		BNX2_WR(bp, BNX2_MISC_ENABLE_SET_BITS,
+			BNX2_MISC_ENABLE_SET_BITS_RX_PARSER_MAC_ENABLE |
+			BNX2_MISC_ENABLE_SET_BITS_TX_HEADER_Q_ENABLE |
+			BNX2_MISC_ENABLE_SET_BITS_EMAC_ENABLE);
 
-			/* receive all multicast */
-			for (i = 0; i < NUM_MC_HASH_REGISTERS; i++) {
-				BNX2_WR(bp, BNX2_EMAC_MULTICAST_HASH0 + (i * 4),
-					0xffffffff);
-			}
-			BNX2_WR(bp, BNX2_EMAC_RX_MODE,
-				BNX2_EMAC_RX_MODE_SORT_MODE);
+		val = BNX2_RD(bp, BNX2_RPM_CONFIG);
+		val &= ~BNX2_RPM_CONFIG_ACPI_ENA;
+		BNX2_WR(bp, BNX2_RPM_CONFIG, val);
 
-			val = 1 | BNX2_RPM_SORT_USER0_BC_EN |
-			      BNX2_RPM_SORT_USER0_MC_EN;
-			BNX2_WR(bp, BNX2_RPM_SORT_USER0, 0x0);
-			BNX2_WR(bp, BNX2_RPM_SORT_USER0, val);
-			BNX2_WR(bp, BNX2_RPM_SORT_USER0, val |
-				BNX2_RPM_SORT_USER0_ENA);
+		wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_WOL;
+	} else {
+			wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL;
+	}
 
-			/* Need to enable EMAC and RPM for WOL. */
-			BNX2_WR(bp, BNX2_MISC_ENABLE_SET_BITS,
-				BNX2_MISC_ENABLE_SET_BITS_RX_PARSER_MAC_ENABLE |
-				BNX2_MISC_ENABLE_SET_BITS_TX_HEADER_Q_ENABLE |
-				BNX2_MISC_ENABLE_SET_BITS_EMAC_ENABLE);
+	if (!(bp->flags & BNX2_FLAG_NO_WOL))
+		bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT3 | wol_msg, 1, 0);
 
-			val = BNX2_RD(bp, BNX2_RPM_CONFIG);
-			val &= ~BNX2_RPM_CONFIG_ACPI_ENA;
-			BNX2_WR(bp, BNX2_RPM_CONFIG, val);
+}
 
-			wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_WOL;
-		}
-		else {
-			wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL;
-		}
+static int
+bnx2_set_power_state(struct bnx2 *bp, pci_power_t state)
+{
+	switch (state) {
+	case PCI_D0: {
+		u32 val;
+
+		pci_enable_wake(bp->pdev, PCI_D0, false);
+		pci_set_power_state(bp->pdev, PCI_D0);
 
-		if (!(bp->flags & BNX2_FLAG_NO_WOL))
-			bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT3 | wol_msg,
-				     1, 0);
+		val = BNX2_RD(bp, BNX2_EMAC_MODE);
+		val |= BNX2_EMAC_MODE_MPKT_RCVD | BNX2_EMAC_MODE_ACPI_RCVD;
+		val &= ~BNX2_EMAC_MODE_MPKT;
+		BNX2_WR(bp, BNX2_EMAC_MODE, val);
 
-		pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+		val = BNX2_RD(bp, BNX2_RPM_CONFIG);
+		val &= ~BNX2_RPM_CONFIG_ACPI_ENA;
+		BNX2_WR(bp, BNX2_RPM_CONFIG, val);
+		break;
+	}
+	case PCI_D3hot: {
+		bnx2_setup_wol(bp);
+		pci_wake_from_d3(bp->pdev, bp->wol);
 		if ((BNX2_CHIP_ID(bp) == BNX2_CHIP_ID_5706_A0) ||
 		    (BNX2_CHIP_ID(bp) == BNX2_CHIP_ID_5706_A1)) {
 
 			if (bp->wol)
-				pmcsr |= 3;
-		}
-		else {
-			pmcsr |= 3;
-		}
-		if (bp->wol) {
-			pmcsr |= PCI_PM_CTRL_PME_ENABLE;
+				pci_set_power_state(bp->pdev, PCI_D3hot);
+		} else {
+			pci_set_power_state(bp->pdev, PCI_D3hot);
 		}
-		pci_write_config_word(bp->pdev, bp->pm_cap + PCI_PM_CTRL,
-				      pmcsr);
 
 		/* No more memory access after this point until
 		 * device is brought back to D0.
 		 */
-		udelay(50);
 		break;
 	}
 	default:
@@ -6317,7 +6301,6 @@ bnx2_open(struct net_device *dev)
 
 	netif_carrier_off(dev);
 
-	bnx2_set_power_state(bp, PCI_D0);
 	bnx2_disable_int(bp);
 
 	rc = bnx2_setup_int_mode(bp, disable_msi);
@@ -6724,7 +6707,6 @@ bnx2_close(struct net_device *dev)
 	bnx2_del_napi(bp);
 	bp->link_up = 0;
 	netif_carrier_off(bp->dev);
-	bnx2_set_power_state(bp, PCI_D3hot);
 	return 0;
 }
 
@@ -7081,6 +7063,9 @@ bnx2_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	else {
 		bp->wol = 0;
 	}
+
+	device_set_wakeup_enable(&bp->pdev->dev, bp->wol);
+
 	return 0;
 }
 
@@ -7156,9 +7141,6 @@ bnx2_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	struct bnx2 *bp = netdev_priv(dev);
 	int rc;
 
-	if (!netif_running(dev))
-		return -EAGAIN;
-
 	/* parameters already validated in ethtool_get_eeprom */
 
 	rc = bnx2_nvram_read(bp, eeprom->offset, eebuf, eeprom->len);
@@ -7173,9 +7155,6 @@ bnx2_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	struct bnx2 *bp = netdev_priv(dev);
 	int rc;
 
-	if (!netif_running(dev))
-		return -EAGAIN;
-
 	/* parameters already validated in ethtool_set_eeprom */
 
 	rc = bnx2_nvram_write(bp, eeprom->offset, eebuf, eeprom->len);
@@ -7535,8 +7514,6 @@ bnx2_self_test(struct net_device *dev, struct ethtool_test *etest, u64 *buf)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
-	bnx2_set_power_state(bp, PCI_D0);
-
 	memset(buf, 0, sizeof(u64) * BNX2_NUM_TESTS);
 	if (etest->flags & ETH_TEST_FL_OFFLINE) {
 		int i;
@@ -7585,8 +7562,6 @@ bnx2_self_test(struct net_device *dev, struct ethtool_test *etest, u64 *buf)
 		etest->flags |= ETH_TEST_FL_FAILED;
 
 	}
-	if (!netif_running(bp->dev))
-		bnx2_set_power_state(bp, PCI_D3hot);
 }
 
 static void
@@ -7658,8 +7633,6 @@ bnx2_set_phys_id(struct net_device *dev, enum ethtool_phys_id_state state)
 
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
-		bnx2_set_power_state(bp, PCI_D0);
-
 		bp->leds_save = BNX2_RD(bp, BNX2_MISC_CFG);
 		BNX2_WR(bp, BNX2_MISC_CFG, BNX2_MISC_CFG_LEDMODE_MAC);
 		return 1;	/* cycle on/off once per second */
@@ -7680,9 +7653,6 @@ bnx2_set_phys_id(struct net_device *dev, enum ethtool_phys_id_state state)
 	case ETHTOOL_ID_INACTIVE:
 		BNX2_WR(bp, BNX2_EMAC_LED, 0);
 		BNX2_WR(bp, BNX2_MISC_CFG, bp->leds_save);
-
-		if (!netif_running(dev))
-			bnx2_set_power_state(bp, PCI_D3hot);
 		break;
 	}
 
@@ -8130,8 +8100,6 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 		goto err_out_release;
 	}
 
-	bnx2_set_power_state(bp, PCI_D0);
-
 	/* Configure byte swap and enable write to the reg_window registers.
 	 * Rely on CPU to do target byte swapping on big endian systems
 	 * The chip's target access swapping will not swap all accesses
@@ -8170,13 +8138,13 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 
 	if (BNX2_CHIP(bp) == BNX2_CHIP_5709 &&
 	    BNX2_CHIP_REV(bp) != BNX2_CHIP_REV_Ax) {
-		if (pci_find_capability(pdev, PCI_CAP_ID_MSIX))
+		if (pdev->msix_cap)
 			bp->flags |= BNX2_FLAG_MSIX_CAP;
 	}
 
 	if (BNX2_CHIP_ID(bp) != BNX2_CHIP_ID_5706_A0 &&
 	    BNX2_CHIP_ID(bp) != BNX2_CHIP_ID_5706_A1) {
-		if (pci_find_capability(pdev, PCI_CAP_ID_MSI))
+		if (pdev->msi_cap)
 			bp->flags |= BNX2_FLAG_MSI_CAP;
 	}
 
@@ -8369,6 +8337,11 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 		bp->wol = 0;
 	}
 
+	if (bp->flags & BNX2_FLAG_NO_WOL)
+		device_set_wakeup_capable(&bp->pdev->dev, false);
+	else
+		device_set_wakeup_enable(&bp->pdev->dev, bp->wol);
+
 	if (BNX2_CHIP_ID(bp) == BNX2_CHIP_ID_5706_A0) {
 		bp->tx_quick_cons_trip_int =
 			bp->tx_quick_cons_trip;
@@ -8609,46 +8582,52 @@ bnx2_remove_one(struct pci_dev *pdev)
 }
 
 static int
-bnx2_suspend(struct pci_dev *pdev, pm_message_t state)
+bnx2_suspend(struct device *device)
 {
+	struct pci_dev *pdev = to_pci_dev(device);
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnx2 *bp = netdev_priv(dev);
 
-	/* PCI register 4 needs to be saved whether netif_running() or not.
-	 * MSI address and data need to be saved if using MSI and
-	 * netif_running().
-	 */
-	pci_save_state(pdev);
-	if (!netif_running(dev))
-		return 0;
-
-	cancel_work_sync(&bp->reset_task);
-	bnx2_netif_stop(bp, true);
-	netif_device_detach(dev);
-	del_timer_sync(&bp->timer);
-	bnx2_shutdown_chip(bp);
-	bnx2_free_skbs(bp);
-	bnx2_set_power_state(bp, pci_choose_state(pdev, state));
+	if (netif_running(dev)) {
+		cancel_work_sync(&bp->reset_task);
+		bnx2_netif_stop(bp, true);
+		netif_device_detach(dev);
+		del_timer_sync(&bp->timer);
+		bnx2_shutdown_chip(bp);
+		__bnx2_free_irq(bp);
+		bnx2_free_skbs(bp);
+	}
+	bnx2_setup_wol(bp);
 	return 0;
 }
 
 static int
-bnx2_resume(struct pci_dev *pdev)
+bnx2_resume(struct device *device)
 {
+	struct pci_dev *pdev = to_pci_dev(device);
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnx2 *bp = netdev_priv(dev);
 
-	pci_restore_state(pdev);
 	if (!netif_running(dev))
 		return 0;
 
 	bnx2_set_power_state(bp, PCI_D0);
 	netif_device_attach(dev);
+	bnx2_request_irq(bp);
 	bnx2_init_nic(bp, 1);
 	bnx2_netif_start(bp, true);
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static SIMPLE_DEV_PM_OPS(bnx2_pm_ops, bnx2_suspend, bnx2_resume);
+#define BNX2_PM_OPS (&bnx2_pm_ops)
+
+#else
+
+#define BNX2_PM_OPS NULL
+
+#endif /* CONFIG_PM_SLEEP */
 /**
  * bnx2_io_error_detected - called when PCI error is detected
  * @pdev: Pointer to PCI device
@@ -8694,24 +8673,28 @@ static pci_ers_result_t bnx2_io_slot_reset(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnx2 *bp = netdev_priv(dev);
-	pci_ers_result_t result;
-	int err;
+	pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
+	int err = 0;
 
 	rtnl_lock();
 	if (pci_enable_device(pdev)) {
 		dev_err(&pdev->dev,
 			"Cannot re-enable PCI device after reset\n");
-		result = PCI_ERS_RESULT_DISCONNECT;
 	} else {
 		pci_set_master(pdev);
 		pci_restore_state(pdev);
 		pci_save_state(pdev);
 
-		if (netif_running(dev)) {
-			bnx2_set_power_state(bp, PCI_D0);
-			bnx2_init_nic(bp, 1);
-		}
-		result = PCI_ERS_RESULT_RECOVERED;
+		if (netif_running(dev))
+			err = bnx2_init_nic(bp, 1);
+
+		if (!err)
+			result = PCI_ERS_RESULT_RECOVERED;
+	}
+
+	if (result != PCI_ERS_RESULT_RECOVERED && netif_running(dev)) {
+		bnx2_napi_enable(bp);
+		dev_close(dev);
 	}
 	rtnl_unlock();
 
@@ -8748,6 +8731,28 @@ static void bnx2_io_resume(struct pci_dev *pdev)
 	rtnl_unlock();
 }
 
+static void bnx2_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnx2 *bp;
+
+	if (!dev)
+		return;
+
+	bp = netdev_priv(dev);
+	if (!bp)
+		return;
+
+	rtnl_lock();
+	if (netif_running(dev))
+		dev_close(bp->dev);
+
+	if (system_state == SYSTEM_POWER_OFF)
+		bnx2_set_power_state(bp, PCI_D3hot);
+
+	rtnl_unlock();
+}
+
 static const struct pci_error_handlers bnx2_err_handler = {
 	.error_detected	= bnx2_io_error_detected,
 	.slot_reset	= bnx2_io_slot_reset,
@@ -8759,9 +8764,9 @@ static struct pci_driver bnx2_pci_driver = {
 	.id_table	= bnx2_pci_tbl,
 	.probe		= bnx2_init_one,
 	.remove		= bnx2_remove_one,
-	.suspend	= bnx2_suspend,
-	.resume		= bnx2_resume,
+	.driver.pm	= BNX2_PM_OPS,
 	.err_handler	= &bnx2_err_handler,
+	.shutdown	= bnx2_shutdown,
 };
 
 module_pci_driver(bnx2_pci_driver);

drivers/net/ethernet/broadcom/bnx2.h

@@ -1,6 +1,6 @@
 /* bnx2.h: Broadcom NX2 network driver.
  *
- * Copyright (c) 2004-2011 Broadcom Corporation
+ * Copyright (c) 2004-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/net/ethernet/broadcom/bnx2x/bnx2x.h

@@ -825,15 +825,13 @@ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
 #define BD_UNMAP_LEN(bd)		(le16_to_cpu((bd)->nbytes))
 
 #define BNX2X_DB_MIN_SHIFT		3	/* 8 bytes */
-#define BNX2X_DB_SHIFT			7	/* 128 bytes*/
+#define BNX2X_DB_SHIFT			3	/* 8 bytes*/
 #if (BNX2X_DB_SHIFT < BNX2X_DB_MIN_SHIFT)
 #error "Min DB doorbell stride is 8"
 #endif
-#define DPM_TRIGER_TYPE			0x40
 #define DOORBELL(bp, cid, val) \
 	do { \
-		writel((u32)(val), bp->doorbells + (bp->db_size * (cid)) + \
-		       DPM_TRIGER_TYPE); \
+		writel((u32)(val), bp->doorbells + (bp->db_size * (cid))); \
 	} while (0)
 
 /* TX CSUM helpers */
@@ -1100,13 +1098,27 @@ struct bnx2x_port {
 extern struct workqueue_struct *bnx2x_wq;
 
 #define BNX2X_MAX_NUM_OF_VFS	64
-#define BNX2X_VF_CID_WND	0
+#define BNX2X_VF_CID_WND	4 /* log num of queues per VF. HW config. */
 #define BNX2X_CIDS_PER_VF	(1 << BNX2X_VF_CID_WND)
-#define BNX2X_CLIENTS_PER_VF	1
-#define BNX2X_FIRST_VF_CID	256
+
+/* We need to reserve doorbell addresses for all VF and queue combinations */
 #define BNX2X_VF_CIDS		(BNX2X_MAX_NUM_OF_VFS * BNX2X_CIDS_PER_VF)
+
+/* The doorbell is configured to have the same number of CIDs for PFs and for
+ * VFs. For this reason the PF CID zone is as large as the VF zone.
+ */
+#define BNX2X_FIRST_VF_CID	BNX2X_VF_CIDS
+#define BNX2X_MAX_NUM_VF_QUEUES	64
 #define BNX2X_VF_ID_INVALID	0xFF
 
+/* the number of VF CIDS multiplied by the amount of bytes reserved for each
+ * cid must not exceed the size of the VF doorbell
+ */
+#define BNX2X_VF_BAR_SIZE	512
+#if (BNX2X_VF_BAR_SIZE < BNX2X_CIDS_PER_VF * (1 << BNX2X_DB_SHIFT))
+#error "VF doorbell bar size is 512"
+#endif
+
 /*
  * The total number of L2 queues, MSIX vectors and HW contexts (CIDs) is
  * control by the number of fast-path status blocks supported by the
@@ -1331,7 +1343,7 @@ enum {
 	BNX2X_SP_RTNL_ENABLE_SRIOV,
 	BNX2X_SP_RTNL_VFPF_MCAST,
 	BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN,
-	BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
+	BNX2X_SP_RTNL_RX_MODE,
 	BNX2X_SP_RTNL_HYPERVISOR_VLAN,
 	BNX2X_SP_RTNL_TX_STOP,
 	BNX2X_SP_RTNL_TX_RESUME,
@@ -1650,10 +1662,10 @@ struct bnx2x {
 	dma_addr_t			fw_stats_data_mapping;
 	int				fw_stats_data_sz;
 
-	/* For max 196 cids (64*3 + non-eth), 32KB ILT page size and 1KB
+	/* For max 1024 cids (VF RSS), 32KB ILT page size and 1KB
 	 * context size we need 8 ILT entries.
 	 */
-#define ILT_MAX_L2_LINES	8
+#define ILT_MAX_L2_LINES	32
 	struct hw_context	context[ILT_MAX_L2_LINES];
 
 	struct bnx2x_ilt	*ilt;
@@ -1869,7 +1881,7 @@ extern int num_queues;
 #define FUNC_FLG_TPA		0x0008
 #define FUNC_FLG_SPQ		0x0010
 #define FUNC_FLG_LEADING	0x0020	/* PF only */
-
+#define FUNC_FLG_LEADING_STATS	0x0040
 struct bnx2x_func_init_params {
 	/* dma */
 	dma_addr_t	fw_stat_map;	/* valid iff FUNC_FLG_STATS */
@@ -2069,9 +2081,8 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms,
 void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
 			    bool is_pf);
 
-#define BNX2X_ILT_ZALLOC(x, y, size)				\
-	x = dma_alloc_coherent(&bp->pdev->dev, size, y,		\
-			       GFP_KERNEL | __GFP_ZERO)
+#define BNX2X_ILT_ZALLOC(x, y, size)					\
+	x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL)
 
 #define BNX2X_ILT_FREE(x, y, size) \
 	do { \

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -1948,7 +1948,7 @@ static void bnx2x_set_rx_buf_size(struct bnx2x *bp)
 	}
 }
 
-static int bnx2x_init_rss_pf(struct bnx2x *bp)
+static int bnx2x_init_rss(struct bnx2x *bp)
 {
 	int i;
 	u8 num_eth_queues = BNX2X_NUM_ETH_QUEUES(bp);
@@ -1972,8 +1972,8 @@ static int bnx2x_init_rss_pf(struct bnx2x *bp)
 	return bnx2x_config_rss_eth(bp, bp->port.pmf || !CHIP_IS_E1x(bp));
 }
 
-int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
-			bool config_hash)
+int bnx2x_rss(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
+	      bool config_hash, bool enable)
 {
 	struct bnx2x_config_rss_params params = {NULL};
 
@@ -1988,17 +1988,21 @@ int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
 
 	__set_bit(RAMROD_COMP_WAIT, &params.ramrod_flags);
 
-	__set_bit(BNX2X_RSS_MODE_REGULAR, &params.rss_flags);
-
-	/* RSS configuration */
-	__set_bit(BNX2X_RSS_IPV4, &params.rss_flags);
-	__set_bit(BNX2X_RSS_IPV4_TCP, &params.rss_flags);
-	__set_bit(BNX2X_RSS_IPV6, &params.rss_flags);
-	__set_bit(BNX2X_RSS_IPV6_TCP, &params.rss_flags);
-	if (rss_obj->udp_rss_v4)
-		__set_bit(BNX2X_RSS_IPV4_UDP, &params.rss_flags);
-	if (rss_obj->udp_rss_v6)
-		__set_bit(BNX2X_RSS_IPV6_UDP, &params.rss_flags);
+	if (enable) {
+		__set_bit(BNX2X_RSS_MODE_REGULAR, &params.rss_flags);
+
+		/* RSS configuration */
+		__set_bit(BNX2X_RSS_IPV4, &params.rss_flags);
+		__set_bit(BNX2X_RSS_IPV4_TCP, &params.rss_flags);
+		__set_bit(BNX2X_RSS_IPV6, &params.rss_flags);
+		__set_bit(BNX2X_RSS_IPV6_TCP, &params.rss_flags);
+		if (rss_obj->udp_rss_v4)
+			__set_bit(BNX2X_RSS_IPV4_UDP, &params.rss_flags);
+		if (rss_obj->udp_rss_v6)
+			__set_bit(BNX2X_RSS_IPV6_UDP, &params.rss_flags);
+	} else {
+		__set_bit(BNX2X_RSS_MODE_DISABLED, &params.rss_flags);
+	}
 
 	/* Hash bits */
 	params.rss_result_mask = MULTI_MASK;
@@ -2007,11 +2011,14 @@ int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
 
 	if (config_hash) {
 		/* RSS keys */
-		prandom_bytes(params.rss_key, sizeof(params.rss_key));
+		prandom_bytes(params.rss_key, T_ETH_RSS_KEY * 4);
 		__set_bit(BNX2X_RSS_SET_SRCH, &params.rss_flags);
 	}
 
-	return bnx2x_config_rss(bp, &params);
+	if (IS_PF(bp))
+		return bnx2x_config_rss(bp, &params);
+	else
+		return bnx2x_vfpf_config_rss(bp, &params);
 }
 
 static int bnx2x_init_hw(struct bnx2x *bp, u32 load_code)
@@ -2066,7 +2073,11 @@ void bnx2x_squeeze_objects(struct bnx2x *bp)
 	rparam.mcast_obj = &bp->mcast_obj;
 	__set_bit(RAMROD_DRV_CLR_ONLY, &rparam.ramrod_flags);
 
-	/* Add a DEL command... */
+	/* Add a DEL command... - Since we're doing a driver cleanup only,
+	 * we take a lock surrounding both the initial send and the CONTs,
+	 * as we don't want a true completion to disrupt us in the middle.
+	 */
+	netif_addr_lock_bh(bp->dev);
 	rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_DEL);
 	if (rc < 0)
 		BNX2X_ERR("Failed to add a new DEL command to a multi-cast object: %d\n",
@@ -2078,11 +2089,13 @@ void bnx2x_squeeze_objects(struct bnx2x *bp)
 		if (rc < 0) {
 			BNX2X_ERR("Failed to clean multi-cast object: %d\n",
 				  rc);
+			netif_addr_unlock_bh(bp->dev);
 			return;
 		}
 
 		rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_CONT);
 	}
+	netif_addr_unlock_bh(bp->dev);
 }
 
 #ifndef BNX2X_STOP_ON_ERROR
@@ -2438,9 +2451,7 @@ int bnx2x_load_cnic(struct bnx2x *bp)
 	}
 
 	/* Initialize Rx filter. */
-	netif_addr_lock_bh(bp->dev);
-	bnx2x_set_rx_mode(bp->dev);
-	netif_addr_unlock_bh(bp->dev);
+	bnx2x_set_rx_mode_inner(bp);
 
 	/* re-read iscsi info */
 	bnx2x_get_iscsi_info(bp);
@@ -2647,38 +2658,32 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 
 		/* initialize FW coalescing state machines in RAM */
 		bnx2x_update_coalesce(bp);
+	}
 
-		/* setup the leading queue */
-		rc = bnx2x_setup_leading(bp);
-		if (rc) {
-			BNX2X_ERR("Setup leading failed!\n");
-			LOAD_ERROR_EXIT(bp, load_error3);
-		}
-
-		/* set up the rest of the queues */
-		for_each_nondefault_eth_queue(bp, i) {
-			rc = bnx2x_setup_queue(bp, &bp->fp[i], 0);
-			if (rc) {
-				BNX2X_ERR("Queue setup failed\n");
-				LOAD_ERROR_EXIT(bp, load_error3);
-			}
-		}
+	/* setup the leading queue */
+	rc = bnx2x_setup_leading(bp);
+	if (rc) {
+		BNX2X_ERR("Setup leading failed!\n");
+		LOAD_ERROR_EXIT(bp, load_error3);
+	}
 
-		/* setup rss */
-		rc = bnx2x_init_rss_pf(bp);
+	/* set up the rest of the queues */
+	for_each_nondefault_eth_queue(bp, i) {
+		if (IS_PF(bp))
+			rc = bnx2x_setup_queue(bp, &bp->fp[i], false);
+		else /* VF */
+			rc = bnx2x_vfpf_setup_q(bp, &bp->fp[i], false);
 		if (rc) {
-			BNX2X_ERR("PF RSS init failed\n");
+			BNX2X_ERR("Queue %d setup failed\n", i);
 			LOAD_ERROR_EXIT(bp, load_error3);
 		}
+	}
 
-	} else { /* vf */
-		for_each_eth_queue(bp, i) {
-			rc = bnx2x_vfpf_setup_q(bp, i);
-			if (rc) {
-				BNX2X_ERR("Queue setup failed\n");
-				LOAD_ERROR_EXIT(bp, load_error3);
-			}
-		}
+	/* setup rss */
+	rc = bnx2x_init_rss(bp);
+	if (rc) {
+		BNX2X_ERR("PF RSS init failed\n");
+		LOAD_ERROR_EXIT(bp, load_error3);
 	}
 
 	/* Now when Clients are configured we are ready to work */
@@ -2710,9 +2715,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 	/* Start fast path */
 
 	/* Initialize Rx filter. */
-	netif_addr_lock_bh(bp->dev);
-	bnx2x_set_rx_mode(bp->dev);
-	netif_addr_unlock_bh(bp->dev);
+	bnx2x_set_rx_mode_inner(bp);
 
 	/* Start the Tx */
 	switch (load_mode) {
@@ -4789,6 +4792,11 @@ int bnx2x_resume(struct pci_dev *pdev)
 void bnx2x_set_ctx_validation(struct bnx2x *bp, struct eth_context *cxt,
 			      u32 cid)
 {
+	if (!cxt) {
+		BNX2X_ERR("bad context pointer %p\n", cxt);
+		return;
+	}
+
 	/* ustorm cxt validation */
 	cxt->ustorm_ag_context.cdu_usage =
 		CDU_RSRVD_VALUE_TYPE_A(HW_CID(bp, cid),

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h

@@ -51,8 +51,7 @@ extern int int_mode;
 
 #define BNX2X_PCI_ALLOC(x, y, size) \
 	do { \
-		x = dma_alloc_coherent(&bp->pdev->dev, size, y, \
-				       GFP_KERNEL | __GFP_ZERO); \
+		x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
 		if (x == NULL) \
 			goto alloc_mem_err; \
 		DP(NETIF_MSG_HW, "BNX2X_PCI_ALLOC: Physical %Lx Virtual %p\n", \
@@ -106,9 +105,10 @@ void bnx2x_send_unload_done(struct bnx2x *bp, bool keep_link);
  * @rss_obj:		RSS object to use
  * @ind_table:		indirection table to configure
  * @config_hash:	re-configure RSS hash keys configuration
+ * @enable:		enabled or disabled configuration
  */
-int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
-			bool config_hash);
+int bnx2x_rss(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
+	      bool config_hash, bool enable);
 
 /**
  * bnx2x__init_func_obj - init function object
@@ -418,6 +418,7 @@ int bnx2x_set_eth_mac(struct bnx2x *bp, bool set);
  * netif_addr_lock_bh()
  */
 void bnx2x_set_rx_mode(struct net_device *dev);
+void bnx2x_set_rx_mode_inner(struct bnx2x *bp);
 
 /**
  * bnx2x_set_storm_rx_mode - configure MAC filtering rules in a FW.
@@ -980,7 +981,7 @@ static inline int func_by_vn(struct bnx2x *bp, int vn)
 
 static inline int bnx2x_config_rss_eth(struct bnx2x *bp, bool config_hash)
 {
-	return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, config_hash);
+	return bnx2x_rss(bp, &bp->rss_conf_obj, config_hash, true);
 }
 
 /**

drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c

@@ -3281,14 +3281,14 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, 0);
+			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
 		} else if ((info->flow_type == UDP_V6_FLOW) &&
 			   (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) {
 			bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested;
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, 0);
+			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
 		}
 		return 0;
 

drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c

@@ -6501,12 +6501,13 @@ static int bnx2x_link_initialize(struct link_params *params,
 		struct bnx2x_phy *phy = &params->phy[INT_PHY];
 		if (vars->line_speed == SPEED_AUTO_NEG &&
 		    (CHIP_IS_E1x(bp) ||
-		     CHIP_IS_E2(bp)))
+		     CHIP_IS_E2(bp))) {
 			bnx2x_set_parallel_detection(phy, params);
 			if (params->phy[INT_PHY].config_init)
 				params->phy[INT_PHY].config_init(phy,
 								 params,
 								 vars);
+		}
 	}
 
 	/* Init external phy*/

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -6893,7 +6893,7 @@ static int bnx2x_init_hw_common(struct bnx2x *bp)
 		bnx2x_init_block(bp, BLOCK_TM, PHASE_COMMON);
 
 	bnx2x_init_block(bp, BLOCK_DORQ, PHASE_COMMON);
-	REG_WR(bp, DORQ_REG_DPM_CID_OFST, BNX2X_DB_SHIFT);
+
 	if (!CHIP_REV_IS_SLOW(bp))
 		/* enable hw interrupt from doorbell Q */
 		REG_WR(bp, DORQ_REG_DORQ_INT_MASK, 0);
@@ -8063,7 +8063,10 @@ int bnx2x_set_eth_mac(struct bnx2x *bp, bool set)
 
 int bnx2x_setup_leading(struct bnx2x *bp)
 {
-	return bnx2x_setup_queue(bp, &bp->fp[0], 1);
+	if (IS_PF(bp))
+		return bnx2x_setup_queue(bp, &bp->fp[0], true);
+	else /* VF */
+		return bnx2x_vfpf_setup_q(bp, &bp->fp[0], true);
 }
 
 /**
@@ -8077,8 +8080,10 @@ int bnx2x_set_int_mode(struct bnx2x *bp)
 {
 	int rc = 0;
 
-	if (IS_VF(bp) && int_mode != BNX2X_INT_MODE_MSIX)
+	if (IS_VF(bp) && int_mode != BNX2X_INT_MODE_MSIX) {
+		BNX2X_ERR("VF not loaded since interrupt mode not msix\n");
 		return -EINVAL;
+	}
 
 	switch (int_mode) {
 	case BNX2X_INT_MODE_MSIX:
@@ -9647,11 +9652,9 @@ sp_rtnl_not_reset:
 		}
 	}
 
-	if (test_and_clear_bit(BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
-			       &bp->sp_rtnl_state)) {
-		DP(BNX2X_MSG_SP,
-		   "sending set storm rx mode vf pf channel message from rtnl sp-task\n");
-		bnx2x_vfpf_storm_rx_mode(bp);
+	if (test_and_clear_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state)) {
+		DP(BNX2X_MSG_SP, "Handling Rx Mode setting\n");
+		bnx2x_set_rx_mode_inner(bp);
 	}
 
 	if (test_and_clear_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN,
@@ -11649,9 +11652,11 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 	 * second status block for the L2 queue, and a third status block for
 	 * CNIC if supported.
 	 */
-	if (CNIC_SUPPORT(bp))
+	if (IS_VF(bp))
+		bp->min_msix_vec_cnt = 1;
+	else if (CNIC_SUPPORT(bp))
 		bp->min_msix_vec_cnt = 3;
-	else
+	else /* PF w/o cnic */
 		bp->min_msix_vec_cnt = 2;
 	BNX2X_DEV_INFO("bp->min_msix_vec_cnt %d", bp->min_msix_vec_cnt);
 
@@ -11868,34 +11873,48 @@ static int bnx2x_set_mc_list(struct bnx2x *bp)
 void bnx2x_set_rx_mode(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
-	u32 rx_mode = BNX2X_RX_MODE_NORMAL;
 
 	if (bp->state != BNX2X_STATE_OPEN) {
 		DP(NETIF_MSG_IFUP, "state is %x, returning\n", bp->state);
 		return;
+	} else {
+		/* Schedule an SP task to handle rest of change */
+		DP(NETIF_MSG_IFUP, "Scheduling an Rx mode change\n");
+		smp_mb__before_clear_bit();
+		set_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state);
+		smp_mb__after_clear_bit();
+		schedule_delayed_work(&bp->sp_rtnl_task, 0);
 	}
+}
+
+void bnx2x_set_rx_mode_inner(struct bnx2x *bp)
+{
+	u32 rx_mode = BNX2X_RX_MODE_NORMAL;
 
 	DP(NETIF_MSG_IFUP, "dev->flags = %x\n", bp->dev->flags);
 
-	if (dev->flags & IFF_PROMISC)
+	netif_addr_lock_bh(bp->dev);
+
+	if (bp->dev->flags & IFF_PROMISC) {
 		rx_mode = BNX2X_RX_MODE_PROMISC;
-	else if ((dev->flags & IFF_ALLMULTI) ||
-		 ((netdev_mc_count(dev) > BNX2X_MAX_MULTICAST) &&
-		  CHIP_IS_E1(bp)))
+	} else if ((bp->dev->flags & IFF_ALLMULTI) ||
+		   ((netdev_mc_count(bp->dev) > BNX2X_MAX_MULTICAST) &&
+		    CHIP_IS_E1(bp))) {
 		rx_mode = BNX2X_RX_MODE_ALLMULTI;
-	else {
+	} else {
 		if (IS_PF(bp)) {
 			/* some multicasts */
 			if (bnx2x_set_mc_list(bp) < 0)
 				rx_mode = BNX2X_RX_MODE_ALLMULTI;
 
+			/* release bh lock, as bnx2x_set_uc_list might sleep */
+			netif_addr_unlock_bh(bp->dev);
 			if (bnx2x_set_uc_list(bp) < 0)
 				rx_mode = BNX2X_RX_MODE_PROMISC;
+			netif_addr_lock_bh(bp->dev);
 		} else {
 			/* configuring mcast to a vf involves sleeping (when we
-			 * wait for the pf's response). Since this function is
-			 * called from non sleepable context we must schedule
-			 * a work item for this purpose
+			 * wait for the pf's response).
 			 */
 			smp_mb__before_clear_bit();
 			set_bit(BNX2X_SP_RTNL_VFPF_MCAST,
@@ -11913,22 +11932,20 @@ void bnx2x_set_rx_mode(struct net_device *dev)
 	/* Schedule the rx_mode command */
 	if (test_bit(BNX2X_FILTER_RX_MODE_PENDING, &bp->sp_state)) {
 		set_bit(BNX2X_FILTER_RX_MODE_SCHED, &bp->sp_state);
+		netif_addr_unlock_bh(bp->dev);
 		return;
 	}
 
 	if (IS_PF(bp)) {
 		bnx2x_set_storm_rx_mode(bp);
+		netif_addr_unlock_bh(bp->dev);
 	} else {
-		/* configuring rx mode to storms in a vf involves sleeping (when
-		 * we wait for the pf's response). Since this function is
-		 * called from non sleepable context we must schedule
-		 * a work item for this purpose
+		/* VF will need to request the PF to make this change, and so
+		 * the VF needs to release the bottom-half lock prior to the
+		 * request (as it will likely require sleep on the VF side)
 		 */
-		smp_mb__before_clear_bit();
-		set_bit(BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
-			&bp->sp_rtnl_state);
-		smp_mb__after_clear_bit();
-		schedule_delayed_work(&bp->sp_rtnl_task, 0);
+		netif_addr_unlock_bh(bp->dev);
+		bnx2x_vfpf_storm_rx_mode(bp);
 	}
 }
 
@@ -12550,19 +12567,16 @@ static int bnx2x_set_qm_cid_count(struct bnx2x *bp)
  * @dev:	pci device
  *
  */
-static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev,
-				     int cnic_cnt, bool is_vf)
+static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev, int cnic_cnt)
 {
-	int pos, index;
+	int index;
 	u16 control = 0;
 
-	pos = pci_find_capability(pdev, PCI_CAP_ID_MSIX);
-
 	/*
 	 * If MSI-X is not supported - return number of SBs needed to support
 	 * one fast path queue: one FP queue + SB for CNIC
 	 */
-	if (!pos) {
+	if (!pdev->msix_cap) {
 		dev_info(&pdev->dev, "no msix capability found\n");
 		return 1 + cnic_cnt;
 	}
@@ -12575,11 +12589,11 @@ static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev,
 	 * without the default SB.
 	 * For VFs there is no default SB, then we return (index+1).
 	 */
-	pci_read_config_word(pdev, pos  + PCI_MSI_FLAGS, &control);
+	pci_read_config_word(pdev, pdev->msix_cap + PCI_MSI_FLAGS, &control);
 
 	index = control & PCI_MSIX_FLAGS_QSIZE;
 
-	return is_vf ? index + 1 : index;
+	return index;
 }
 
 static int set_max_cos_est(int chip_id)
@@ -12659,10 +12673,13 @@ static int bnx2x_init_one(struct pci_dev *pdev,
 	is_vf = set_is_vf(ent->driver_data);
 	cnic_cnt = is_vf ? 0 : 1;
 
-	max_non_def_sbs = bnx2x_get_num_non_def_sbs(pdev, cnic_cnt, is_vf);
+	max_non_def_sbs = bnx2x_get_num_non_def_sbs(pdev, cnic_cnt);
+
+	/* add another SB for VF as it has no default SB */
+	max_non_def_sbs += is_vf ? 1 : 0;
 
 	/* Maximum number of RSS queues: one IGU SB goes to CNIC */
-	rss_count = is_vf ? 1 : max_non_def_sbs - cnic_cnt;
+	rss_count = max_non_def_sbs - cnic_cnt;
 
 	if (rss_count < 1)
 		return -EINVAL;

drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h

@@ -6335,6 +6335,7 @@
 #define PCI_ID_VAL2					0x438
 #define PCI_ID_VAL3					0x43c
 
+#define GRC_CONFIG_REG_VF_MSIX_CONTROL		    0x61C
 #define GRC_CONFIG_REG_PF_INIT_VF		0x624
 #define GRC_CR_PF_INIT_VF_PF_FIRST_VF_NUM_MASK	0xf
 /* First VF_NUM for PF is encoded in this register.

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c

@@ -159,16 +159,6 @@ static inline void __bnx2x_exe_queue_reset_pending(
 	}
 }
 
-static inline void bnx2x_exe_queue_reset_pending(struct bnx2x *bp,
-						 struct bnx2x_exe_queue_obj *o)
-{
-	spin_lock_bh(&o->lock);
-
-	__bnx2x_exe_queue_reset_pending(bp, o);
-
-	spin_unlock_bh(&o->lock);
-}
-
 /**
  * bnx2x_exe_queue_step - execute one execution chunk atomically
  *
@@ -176,7 +166,7 @@ static inline void bnx2x_exe_queue_reset_pending(struct bnx2x *bp,
  * @o:			queue
  * @ramrod_flags:	flags
  *
- * (Atomicity is ensured using the exe_queue->lock).
+ * (Should be called while holding the exe_queue->lock).
  */
 static inline int bnx2x_exe_queue_step(struct bnx2x *bp,
 				       struct bnx2x_exe_queue_obj *o,
@@ -187,8 +177,6 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp,
 
 	memset(&spacer, 0, sizeof(spacer));
 
-	spin_lock_bh(&o->lock);
-
 	/* Next step should not be performed until the current is finished,
 	 * unless a DRV_CLEAR_ONLY bit is set. In this case we just want to
 	 * properly clear object internals without sending any command to the FW
@@ -200,7 +188,6 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp,
 			DP(BNX2X_MSG_SP, "RAMROD_DRV_CLR_ONLY requested: resetting a pending_comp list\n");
 			__bnx2x_exe_queue_reset_pending(bp, o);
 		} else {
-			spin_unlock_bh(&o->lock);
 			return 1;
 		}
 	}
@@ -228,10 +215,8 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp,
 	}
 
 	/* Sanity check */
-	if (!cur_len) {
-		spin_unlock_bh(&o->lock);
+	if (!cur_len)
 		return 0;
-	}
 
 	rc = o->execute(bp, o->owner, &o->pending_comp, ramrod_flags);
 	if (rc < 0)
@@ -245,7 +230,6 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp,
 		 */
 		__bnx2x_exe_queue_reset_pending(bp, o);
 
-	spin_unlock_bh(&o->lock);
 	return rc;
 }
 
@@ -432,12 +416,219 @@ static bool bnx2x_put_credit_vlan_mac(struct bnx2x_vlan_mac_obj *o)
 	return true;
 }
 
+/**
+ * __bnx2x_vlan_mac_h_write_trylock - try getting the vlan mac writer lock
+ *
+ * @bp:		device handle
+ * @o:		vlan_mac object
+ *
+ * @details: Non-blocking implementation; should be called under execution
+ *           queue lock.
+ */
+static int __bnx2x_vlan_mac_h_write_trylock(struct bnx2x *bp,
+					    struct bnx2x_vlan_mac_obj *o)
+{
+	if (o->head_reader) {
+		DP(BNX2X_MSG_SP, "vlan_mac_lock writer - There are readers; Busy\n");
+		return -EBUSY;
+	}
+
+	DP(BNX2X_MSG_SP, "vlan_mac_lock writer - Taken\n");
+	return 0;
+}
+
+/**
+ * __bnx2x_vlan_mac_h_exec_pending - execute step instead of a previous step
+ *
+ * @bp:		device handle
+ * @o:		vlan_mac object
+ *
+ * @details Should be called under execution queue lock; notice it might release
+ *          and reclaim it during its run.
+ */
+static void __bnx2x_vlan_mac_h_exec_pending(struct bnx2x *bp,
+					    struct bnx2x_vlan_mac_obj *o)
+{
+	int rc;
+	unsigned long ramrod_flags = o->saved_ramrod_flags;
+
+	DP(BNX2X_MSG_SP, "vlan_mac_lock execute pending command with ramrod flags %lu\n",
+	   ramrod_flags);
+	o->head_exe_request = false;
+	o->saved_ramrod_flags = 0;
+	rc = bnx2x_exe_queue_step(bp, &o->exe_queue, &ramrod_flags);
+	if (rc != 0) {
+		BNX2X_ERR("execution of pending commands failed with rc %d\n",
+			  rc);
+#ifdef BNX2X_STOP_ON_ERROR
+		bnx2x_panic();
+#endif
+	}
+}
+
+/**
+ * __bnx2x_vlan_mac_h_pend - Pend an execution step which couldn't run
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ * @ramrod_flags:	ramrod flags of missed execution
+ *
+ * @details Should be called under execution queue lock.
+ */
+static void __bnx2x_vlan_mac_h_pend(struct bnx2x *bp,
+				    struct bnx2x_vlan_mac_obj *o,
+				    unsigned long ramrod_flags)
+{
+	o->head_exe_request = true;
+	o->saved_ramrod_flags = ramrod_flags;
+	DP(BNX2X_MSG_SP, "Placing pending execution with ramrod flags %lu\n",
+	   ramrod_flags);
+}
+
+/**
+ * __bnx2x_vlan_mac_h_write_unlock - unlock the vlan mac head list writer lock
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ *
+ * @details Should be called under execution queue lock. Notice if a pending
+ *          execution exists, it would perform it - possibly releasing and
+ *          reclaiming the execution queue lock.
+ */
+static void __bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp,
+					    struct bnx2x_vlan_mac_obj *o)
+{
+	/* It's possible a new pending execution was added since this writer
+	 * executed. If so, execute again. [Ad infinitum]
+	 */
+	while (o->head_exe_request) {
+		DP(BNX2X_MSG_SP, "vlan_mac_lock - writer release encountered a pending request\n");
+		__bnx2x_vlan_mac_h_exec_pending(bp, o);
+	}
+}
+
+/**
+ * bnx2x_vlan_mac_h_write_unlock - unlock the vlan mac head list writer lock
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ *
+ * @details Notice if a pending execution exists, it would perform it -
+ *          possibly releasing and reclaiming the execution queue lock.
+ */
+void bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp,
+				   struct bnx2x_vlan_mac_obj *o)
+{
+	spin_lock_bh(&o->exe_queue.lock);
+	__bnx2x_vlan_mac_h_write_unlock(bp, o);
+	spin_unlock_bh(&o->exe_queue.lock);
+}
+
+/**
+ * __bnx2x_vlan_mac_h_read_lock - lock the vlan mac head list reader lock
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ *
+ * @details Should be called under the execution queue lock. May sleep. May
+ *          release and reclaim execution queue lock during its run.
+ */
+static int __bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
+					struct bnx2x_vlan_mac_obj *o)
+{
+	/* If we got here, we're holding lock --> no WRITER exists */
+	o->head_reader++;
+	DP(BNX2X_MSG_SP, "vlan_mac_lock - locked reader - number %d\n",
+	   o->head_reader);
+
+	return 0;
+}
+
+/**
+ * bnx2x_vlan_mac_h_read_lock - lock the vlan mac head list reader lock
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ *
+ * @details May sleep. Claims and releases execution queue lock during its run.
+ */
+int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
+			       struct bnx2x_vlan_mac_obj *o)
+{
+	int rc;
+
+	spin_lock_bh(&o->exe_queue.lock);
+	rc = __bnx2x_vlan_mac_h_read_lock(bp, o);
+	spin_unlock_bh(&o->exe_queue.lock);
+
+	return rc;
+}
+
+/**
+ * __bnx2x_vlan_mac_h_read_unlock - unlock the vlan mac head list reader lock
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ *
+ * @details Should be called under execution queue lock. Notice if a pending
+ *          execution exists, it would be performed if this was the last
+ *          reader. possibly releasing and reclaiming the execution queue lock.
+ */
+static void __bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp,
+					  struct bnx2x_vlan_mac_obj *o)
+{
+	if (!o->head_reader) {
+		BNX2X_ERR("Need to release vlan mac reader lock, but lock isn't taken\n");
+#ifdef BNX2X_STOP_ON_ERROR
+		bnx2x_panic();
+#endif
+	} else {
+		o->head_reader--;
+		DP(BNX2X_MSG_SP, "vlan_mac_lock - decreased readers to %d\n",
+		   o->head_reader);
+	}
+
+	/* It's possible a new pending execution was added, and that this reader
+	 * was last - if so we need to execute the command.
+	 */
+	if (!o->head_reader && o->head_exe_request) {
+		DP(BNX2X_MSG_SP, "vlan_mac_lock - reader release encountered a pending request\n");
+
+		/* Writer release will do the trick */
+		__bnx2x_vlan_mac_h_write_unlock(bp, o);
+	}
+}
+
+/**
+ * bnx2x_vlan_mac_h_read_unlock - unlock the vlan mac head list reader lock
+ *
+ * @bp:			device handle
+ * @o:			vlan_mac object
+ *
+ * @details Notice if a pending execution exists, it would be performed if this
+ *          was the last reader. Claims and releases the execution queue lock
+ *          during its run.
+ */
+void bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp,
+				  struct bnx2x_vlan_mac_obj *o)
+{
+	spin_lock_bh(&o->exe_queue.lock);
+	__bnx2x_vlan_mac_h_read_unlock(bp, o);
+	spin_unlock_bh(&o->exe_queue.lock);
+}
+
 static int bnx2x_get_n_elements(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o,
 				int n, u8 *base, u8 stride, u8 size)
 {
 	struct bnx2x_vlan_mac_registry_elem *pos;
 	u8 *next = base;
 	int counter = 0;
+	int read_lock;
+
+	DP(BNX2X_MSG_SP, "get_n_elements - taking vlan_mac_lock (reader)\n");
+	read_lock = bnx2x_vlan_mac_h_read_lock(bp, o);
+	if (read_lock != 0)
+		BNX2X_ERR("get_n_elements failed to get vlan mac reader lock; Access without lock\n");
 
 	/* traverse list */
 	list_for_each_entry(pos, &o->head, link) {
@@ -449,6 +640,12 @@ static int bnx2x_get_n_elements(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o,
 			next += stride + size;
 		}
 	}
+
+	if (read_lock == 0) {
+		DP(BNX2X_MSG_SP, "get_n_elements - releasing vlan_mac_lock (reader)\n");
+		bnx2x_vlan_mac_h_read_unlock(bp, o);
+	}
+
 	return counter * ETH_ALEN;
 }
 
@@ -1397,6 +1594,32 @@ static int bnx2x_wait_vlan_mac(struct bnx2x *bp,
 	return -EBUSY;
 }
 
+static int __bnx2x_vlan_mac_execute_step(struct bnx2x *bp,
+					 struct bnx2x_vlan_mac_obj *o,
+					 unsigned long *ramrod_flags)
+{
+	int rc = 0;
+
+	spin_lock_bh(&o->exe_queue.lock);
+
+	DP(BNX2X_MSG_SP, "vlan_mac_execute_step - trying to take writer lock\n");
+	rc = __bnx2x_vlan_mac_h_write_trylock(bp, o);
+
+	if (rc != 0) {
+		__bnx2x_vlan_mac_h_pend(bp, o, *ramrod_flags);
+
+		/* Calling function should not diffrentiate between this case
+		 * and the case in which there is already a pending ramrod
+		 */
+		rc = 1;
+	} else {
+		rc = bnx2x_exe_queue_step(bp, &o->exe_queue, ramrod_flags);
+	}
+	spin_unlock_bh(&o->exe_queue.lock);
+
+	return rc;
+}
+
 /**
  * bnx2x_complete_vlan_mac - complete one VLAN-MAC ramrod
  *
@@ -1414,19 +1637,27 @@ static int bnx2x_complete_vlan_mac(struct bnx2x *bp,
 	struct bnx2x_raw_obj *r = &o->raw;
 	int rc;
 
+	/* Clearing the pending list & raw state should be made
+	 * atomically (as execution flow assumes they represent the same).
+	 */
+	spin_lock_bh(&o->exe_queue.lock);
+
 	/* Reset pending list */
-	bnx2x_exe_queue_reset_pending(bp, &o->exe_queue);
+	__bnx2x_exe_queue_reset_pending(bp, &o->exe_queue);
 
 	/* Clear pending */
 	r->clear_pending(r);
 
+	spin_unlock_bh(&o->exe_queue.lock);
+
 	/* If ramrod failed this is most likely a SW bug */
 	if (cqe->message.error)
 		return -EINVAL;
 
 	/* Run the next bulk of pending commands if requested */
 	if (test_bit(RAMROD_CONT, ramrod_flags)) {
-		rc = bnx2x_exe_queue_step(bp, &o->exe_queue, ramrod_flags);
+		rc = __bnx2x_vlan_mac_execute_step(bp, o, ramrod_flags);
+
 		if (rc < 0)
 			return rc;
 	}
@@ -1719,9 +1950,8 @@ static inline int bnx2x_vlan_mac_push_new_cmd(
  * @p:
  *
  */
-int bnx2x_config_vlan_mac(
-	struct bnx2x *bp,
-	struct bnx2x_vlan_mac_ramrod_params *p)
+int bnx2x_config_vlan_mac(struct bnx2x *bp,
+			   struct bnx2x_vlan_mac_ramrod_params *p)
 {
 	int rc = 0;
 	struct bnx2x_vlan_mac_obj *o = p->vlan_mac_obj;
@@ -1752,7 +1982,8 @@ int bnx2x_config_vlan_mac(
 	/* Execute commands if required */
 	if (cont || test_bit(RAMROD_EXEC, ramrod_flags) ||
 	    test_bit(RAMROD_COMP_WAIT, ramrod_flags)) {
-		rc = bnx2x_exe_queue_step(bp, &o->exe_queue, ramrod_flags);
+		rc = __bnx2x_vlan_mac_execute_step(bp, p->vlan_mac_obj,
+						   &p->ramrod_flags);
 		if (rc < 0)
 			return rc;
 	}
@@ -1775,8 +2006,9 @@ int bnx2x_config_vlan_mac(
 				return rc;
 
 			/* Make a next step */
-			rc = bnx2x_exe_queue_step(bp, &o->exe_queue,
-						  ramrod_flags);
+			rc = __bnx2x_vlan_mac_execute_step(bp,
+							   p->vlan_mac_obj,
+							   &p->ramrod_flags);
 			if (rc < 0)
 				return rc;
 		}
@@ -1806,10 +2038,11 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp,
 				  unsigned long *ramrod_flags)
 {
 	struct bnx2x_vlan_mac_registry_elem *pos = NULL;
-	int rc = 0;
 	struct bnx2x_vlan_mac_ramrod_params p;
 	struct bnx2x_exe_queue_obj *exeq = &o->exe_queue;
 	struct bnx2x_exeq_elem *exeq_pos, *exeq_pos_n;
+	int read_lock;
+	int rc = 0;
 
 	/* Clear pending commands first */
 
@@ -1844,6 +2077,11 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp,
 	__clear_bit(RAMROD_EXEC, &p.ramrod_flags);
 	__clear_bit(RAMROD_CONT, &p.ramrod_flags);
 
+	DP(BNX2X_MSG_SP, "vlan_mac_del_all -- taking vlan_mac_lock (reader)\n");
+	read_lock = bnx2x_vlan_mac_h_read_lock(bp, o);
+	if (read_lock != 0)
+		return read_lock;
+
 	list_for_each_entry(pos, &o->head, link) {
 		if (pos->vlan_mac_flags == *vlan_mac_flags) {
 			p.user_req.vlan_mac_flags = pos->vlan_mac_flags;
@@ -1851,11 +2089,15 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp,
 			rc = bnx2x_config_vlan_mac(bp, &p);
 			if (rc < 0) {
 				BNX2X_ERR("Failed to add a new DEL command\n");
+				bnx2x_vlan_mac_h_read_unlock(bp, o);
 				return rc;
 			}
 		}
 	}
 
+	DP(BNX2X_MSG_SP, "vlan_mac_del_all -- releasing vlan_mac_lock (reader)\n");
+	bnx2x_vlan_mac_h_read_unlock(bp, o);
+
 	p.ramrod_flags = *ramrod_flags;
 	__set_bit(RAMROD_CONT, &p.ramrod_flags);
 
@@ -1887,6 +2129,9 @@ static inline void bnx2x_init_vlan_mac_common(struct bnx2x_vlan_mac_obj *o,
 	struct bnx2x_credit_pool_obj *vlans_pool)
 {
 	INIT_LIST_HEAD(&o->head);
+	o->head_reader = 0;
+	o->head_exe_request = false;
+	o->saved_ramrod_flags = 0;
 
 	o->macs_pool = macs_pool;
 	o->vlans_pool = vlans_pool;
@@ -4171,6 +4416,16 @@ void bnx2x_init_rss_config_obj(struct bnx2x *bp,
 	rss_obj->config_rss = bnx2x_setup_rss;
 }
 
+int validate_vlan_mac(struct bnx2x *bp,
+		      struct bnx2x_vlan_mac_obj *vlan_mac)
+{
+	if (!vlan_mac->get_n_elements) {
+		BNX2X_ERR("vlan mac object was not intialized\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /********************** Queue state object ***********************************/
 
 /**

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h

@@ -285,6 +285,12 @@ struct bnx2x_vlan_mac_obj {
 	 * entries.
 	 */
 	struct list_head		head;
+	/* Implement a simple reader/writer lock on the head list.
+	 * all these fields should only be accessed under the exe_queue lock
+	 */
+	u8		head_reader; /* Num. of readers accessing head list */
+	bool		head_exe_request; /* Pending execution request. */
+	unsigned long	saved_ramrod_flags; /* Ramrods of pending execution */
 
 	/* TODO: Add it's initialization in the init functions */
 	struct bnx2x_exe_queue_obj	exe_queue;
@@ -1302,8 +1308,16 @@ void bnx2x_init_vlan_mac_obj(struct bnx2x *bp,
 			     struct bnx2x_credit_pool_obj *macs_pool,
 			     struct bnx2x_credit_pool_obj *vlans_pool);
 
+int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
+					struct bnx2x_vlan_mac_obj *o);
+void bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp,
+				  struct bnx2x_vlan_mac_obj *o);
+int bnx2x_vlan_mac_h_write_lock(struct bnx2x *bp,
+				struct bnx2x_vlan_mac_obj *o);
+void bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp,
+					  struct bnx2x_vlan_mac_obj *o);
 int bnx2x_config_vlan_mac(struct bnx2x *bp,
-			  struct bnx2x_vlan_mac_ramrod_params *p);
+			   struct bnx2x_vlan_mac_ramrod_params *p);
 
 int bnx2x_vlan_mac_move(struct bnx2x *bp,
 			struct bnx2x_vlan_mac_ramrod_params *p,
@@ -1393,4 +1407,6 @@ int bnx2x_config_rss(struct bnx2x *bp,
 void bnx2x_get_rss_ind_table(struct bnx2x_rss_config_obj *rss_obj,
 			     u8 *ind_table);
 
+int validate_vlan_mac(struct bnx2x *bp,
+		      struct bnx2x_vlan_mac_obj *vlan_mac);
 #endif /* BNX2X_SP_VERBS */

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c

@@ -170,6 +170,11 @@ enum bnx2x_vfop_qteardown_state {
 	   BNX2X_VFOP_QTEARDOWN_DONE
 };
 
+enum bnx2x_vfop_rss_state {
+	   BNX2X_VFOP_RSS_CONFIG,
+	   BNX2X_VFOP_RSS_DONE
+};
+
 #define bnx2x_vfop_reset_wq(vf)	atomic_set(&vf->op_in_progress, 0)
 
 void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
@@ -265,11 +270,6 @@ void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
 	__set_bit(BNX2X_Q_FLG_TX_SEC, &setup_p->flags);
 	__set_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags);
 
-	if (vfq_is_leading(q)) {
-		__set_bit(BNX2X_Q_FLG_LEADING_RSS, &setup_p->flags);
-		__set_bit(BNX2X_Q_FLG_MCAST, &setup_p->flags);
-	}
-
 	/* Setup-op rx parameters */
 	if (test_bit(BNX2X_Q_TYPE_HAS_RX, &q_type)) {
 		struct bnx2x_rxq_setup_params *rxq_p = &setup_p->rxq_params;
@@ -398,7 +398,11 @@ static void bnx2x_vfop_qdtor(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		    BNX2X_Q_LOGICAL_STATE_STOPPED) {
 			DP(BNX2X_MSG_IOV,
 			   "Entered qdtor but queue was already stopped. Aborting gracefully\n");
-			goto op_done;
+
+			/* next state */
+			vfop->state = BNX2X_VFOP_QDTOR_DONE;
+
+			bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
 		}
 
 		/* next state */
@@ -432,8 +436,10 @@ op_err:
 op_done:
 	case BNX2X_VFOP_QDTOR_DONE:
 		/* invalidate the context */
-		qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
-		qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+		if (qdtor->cxt) {
+			qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
+			qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+		}
 		bnx2x_vfop_end(bp, vf, vfop);
 		return;
 	default:
@@ -465,7 +471,8 @@ static int bnx2x_vfop_qdtor_cmd(struct bnx2x *bp,
 		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdtor,
 					     cmd->block);
 	}
-	DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop.\n", vf->abs_vfid);
+	DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop. rc %d\n",
+	   vf->abs_vfid, vfop->rc);
 	return -ENOMEM;
 }
 
@@ -474,10 +481,18 @@ bnx2x_vf_set_igu_info(struct bnx2x *bp, u8 igu_sb_id, u8 abs_vfid)
 {
 	struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid);
 	if (vf) {
+		/* the first igu entry belonging to VFs of this PF */
+		if (!BP_VFDB(bp)->first_vf_igu_entry)
+			BP_VFDB(bp)->first_vf_igu_entry = igu_sb_id;
+
+		/* the first igu entry belonging to this VF */
 		if (!vf_sb_count(vf))
 			vf->igu_base_id = igu_sb_id;
+
 		++vf_sb_count(vf);
+		++vf->sb_count;
 	}
+	BP_VFDB(bp)->vf_sbs_pool++;
 }
 
 /* VFOP MAC/VLAN helpers */
@@ -491,12 +506,20 @@ static inline void bnx2x_vfop_credit(struct bnx2x *bp,
 	 * and a valid credit counter
 	 */
 	if (!vfop->rc && args->credit) {
-		int cnt = 0;
 		struct list_head *pos;
+		int read_lock;
+		int cnt = 0;
+
+		read_lock = bnx2x_vlan_mac_h_read_lock(bp, obj);
+		if (read_lock)
+			DP(BNX2X_MSG_SP, "Failed to take vlan mac read head; continuing anyway\n");
 
 		list_for_each(pos, &obj->head)
 			cnt++;
 
+		if (!read_lock)
+			bnx2x_vlan_mac_h_read_unlock(bp, obj);
+
 		atomic_set(args->credit, cnt);
 	}
 }
@@ -692,6 +715,7 @@ static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp,
 				     int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -711,6 +735,9 @@ static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp,
 		bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
 
 		/* set extra args */
@@ -731,6 +758,7 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
 			    int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -753,6 +781,9 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
 		bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
 
 		/* set extra args */
@@ -773,6 +804,7 @@ int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 			    int qid, u16 vid, bool add)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -793,6 +825,9 @@ int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 		ramrod->user_req.u.vlan.vlan = vid;
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
 
 		/* set extra args */
@@ -812,6 +847,7 @@ static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp,
 			       int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -831,6 +867,9 @@ static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp,
 		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
 
 		/* set extra args */
@@ -851,6 +890,7 @@ int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
 			     int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -870,6 +910,9 @@ int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
 		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
 
 		/* set extra args */
@@ -980,21 +1023,25 @@ static void bnx2x_vfop_qflr(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	case BNX2X_VFOP_QFLR_CLR_VLAN:
 		/* vlan-clear-all: driver-only, don't consume credit */
 		vfop->state = BNX2X_VFOP_QFLR_CLR_MAC;
-		vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, true);
+		if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj)))
+			vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid,
+							      true);
 		if (vfop->rc)
 			goto op_err;
-		return;
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
 
 	case BNX2X_VFOP_QFLR_CLR_MAC:
 		/* mac-clear-all: driver only consume credit */
 		vfop->state = BNX2X_VFOP_QFLR_TERMINATE;
-		vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, true);
+		if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj)))
+			vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid,
+							     true);
 		DP(BNX2X_MSG_IOV,
 		   "VF[%d] vfop->rc after bnx2x_vfop_mac_delall_cmd was %d",
 		   vf->abs_vfid, vfop->rc);
 		if (vfop->rc)
 			goto op_err;
-		return;
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
 
 	case BNX2X_VFOP_QFLR_TERMINATE:
 		qstate = &vfop->op_p->qctor.qstate;
@@ -1291,10 +1338,13 @@ int bnx2x_vfop_qdown_cmd(struct bnx2x *bp,
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
 
+	/* for non leading queues skip directly to qdown sate */
 	if (vfop) {
 		vfop->args.qx.qid = qid;
-		bnx2x_vfop_opset(BNX2X_VFOP_QTEARDOWN_RXMODE,
-				 bnx2x_vfop_qdown, cmd->done);
+		bnx2x_vfop_opset(qid == LEADING_IDX ?
+				 BNX2X_VFOP_QTEARDOWN_RXMODE :
+				 BNX2X_VFOP_QTEARDOWN_QDTOR, bnx2x_vfop_qdown,
+				 cmd->done);
 		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdown,
 					     cmd->block);
 	}
@@ -1447,15 +1497,16 @@ int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid)
  * both known
  */
 static void
-bnx2x_iov_static_resc(struct bnx2x *bp, struct vf_pf_resc_request *resc)
+bnx2x_iov_static_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
+	struct vf_pf_resc_request *resc = &vf->alloc_resc;
 	u16 vlan_count = 0;
 
 	/* will be set only during VF-ACQUIRE */
 	resc->num_rxqs = 0;
 	resc->num_txqs = 0;
 
-	/* no credit calculcis for macs (just yet) */
+	/* no credit calculations for macs (just yet) */
 	resc->num_mac_filters = 1;
 
 	/* divvy up vlan rules */
@@ -1467,13 +1518,14 @@ bnx2x_iov_static_resc(struct bnx2x *bp, struct vf_pf_resc_request *resc)
 	resc->num_mc_filters = 0;
 
 	/* num_sbs already set */
+	resc->num_sbs = vf->sb_count;
 }
 
 /* FLR routines: */
 static void bnx2x_vf_free_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
 	/* reset the state variables */
-	bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+	bnx2x_iov_static_resc(bp, vf);
 	vf->state = VF_FREE;
 }
 
@@ -1693,8 +1745,7 @@ void bnx2x_iov_init_dq(struct bnx2x *bp)
 	/* The VF doorbell size  0 - *B, 4 - 128B. We set it here to match
 	 * the Pf doorbell size although the 2 are independent.
 	 */
-	REG_WR(bp, DORQ_REG_VF_NORM_CID_OFST,
-	       BNX2X_DB_SHIFT - BNX2X_DB_MIN_SHIFT);
+	REG_WR(bp, DORQ_REG_VF_NORM_CID_OFST, 3);
 
 	/* No security checks for now -
 	 * configure single rule (out of 16) mask = 0x1, value = 0x0,
@@ -1761,7 +1812,7 @@ bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
 {
 	int sb_id;
 	u32 val;
-	u8 fid;
+	u8 fid, current_pf = 0;
 
 	/* IGU in normal mode - read CAM */
 	for (sb_id = 0; sb_id < IGU_REG_MAPPING_MEMORY_SIZE; sb_id++) {
@@ -1769,16 +1820,18 @@ bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
 		if (!(val & IGU_REG_MAPPING_MEMORY_VALID))
 			continue;
 		fid = GET_FIELD((val), IGU_REG_MAPPING_MEMORY_FID);
-		if (!(fid & IGU_FID_ENCODE_IS_PF))
+		if (fid & IGU_FID_ENCODE_IS_PF)
+			current_pf = fid & IGU_FID_PF_NUM_MASK;
+		else if (current_pf == BP_ABS_FUNC(bp))
 			bnx2x_vf_set_igu_info(bp, sb_id,
 					      (fid & IGU_FID_VF_NUM_MASK));
-
 		DP(BNX2X_MSG_IOV, "%s[%d], igu_sb_id=%d, msix=%d\n",
 		   ((fid & IGU_FID_ENCODE_IS_PF) ? "PF" : "VF"),
 		   ((fid & IGU_FID_ENCODE_IS_PF) ? (fid & IGU_FID_PF_NUM_MASK) :
 		   (fid & IGU_FID_VF_NUM_MASK)), sb_id,
 		   GET_FIELD((val), IGU_REG_MAPPING_MEMORY_VECTOR));
 	}
+	DP(BNX2X_MSG_IOV, "vf_sbs_pool is %d\n", BP_VFDB(bp)->vf_sbs_pool);
 }
 
 static void __bnx2x_iov_free_vfdb(struct bnx2x *bp)
@@ -1844,23 +1897,11 @@ static int bnx2x_sriov_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
 	return 0;
 }
 
-static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
-{
-	int i;
-	u8 queue_count = 0;
-
-	if (IS_SRIOV(bp))
-		for_each_vf(bp, i)
-			queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
-
-	return queue_count;
-}
-
 /* must be called after PF bars are mapped */
 int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
-			int num_vfs_param)
+		       int num_vfs_param)
 {
-	int err, i, qcount;
+	int err, i;
 	struct bnx2x_sriov *iov;
 	struct pci_dev *dev = bp->pdev;
 
@@ -1958,12 +1999,13 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
 	/* re-read the IGU CAM for VFs - index and abs_vfid must be set */
 	bnx2x_get_vf_igu_cam_info(bp);
 
-	/* get the total queue count and allocate the global queue arrays */
-	qcount = bnx2x_iov_get_max_queue_count(bp);
-
 	/* allocate the queue arrays for all VFs */
-	bp->vfdb->vfqs = kzalloc(qcount * sizeof(struct bnx2x_vf_queue),
-				 GFP_KERNEL);
+	bp->vfdb->vfqs = kzalloc(
+		BNX2X_MAX_NUM_VF_QUEUES * sizeof(struct bnx2x_vf_queue),
+		GFP_KERNEL);
+
+	DP(BNX2X_MSG_IOV, "bp->vfdb->vfqs was %p\n", bp->vfdb->vfqs);
+
 	if (!bp->vfdb->vfqs) {
 		BNX2X_ERR("failed to allocate vf queue array\n");
 		err = -ENOMEM;
@@ -2084,49 +2126,14 @@ static void bnx2x_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			     q_type);
 
 	DP(BNX2X_MSG_IOV,
-	   "initialized vf %d's queue object. func id set to %d\n",
-	   vf->abs_vfid, q->sp_obj.func_id);
-
-	/* mac/vlan objects are per queue, but only those
-	 * that belong to the leading queue are initialized
-	 */
-	if (vfq_is_leading(q)) {
-		/* mac */
-		bnx2x_init_mac_obj(bp, &q->mac_obj,
-				   cl_id, q->cid, func_id,
-				   bnx2x_vf_sp(bp, vf, mac_rdata),
-				   bnx2x_vf_sp_map(bp, vf, mac_rdata),
-				   BNX2X_FILTER_MAC_PENDING,
-				   &vf->filter_state,
-				   BNX2X_OBJ_TYPE_RX_TX,
-				   &bp->macs_pool);
-		/* vlan */
-		bnx2x_init_vlan_obj(bp, &q->vlan_obj,
-				    cl_id, q->cid, func_id,
-				    bnx2x_vf_sp(bp, vf, vlan_rdata),
-				    bnx2x_vf_sp_map(bp, vf, vlan_rdata),
-				    BNX2X_FILTER_VLAN_PENDING,
-				    &vf->filter_state,
-				    BNX2X_OBJ_TYPE_RX_TX,
-				    &bp->vlans_pool);
-
-		/* mcast */
-		bnx2x_init_mcast_obj(bp, &vf->mcast_obj, cl_id,
-				     q->cid, func_id, func_id,
-				     bnx2x_vf_sp(bp, vf, mcast_rdata),
-				     bnx2x_vf_sp_map(bp, vf, mcast_rdata),
-				     BNX2X_FILTER_MCAST_PENDING,
-				     &vf->filter_state,
-				     BNX2X_OBJ_TYPE_RX_TX);
-
-		vf->leading_rss = cl_id;
-	}
+	   "initialized vf %d's queue object. func id set to %d. cid set to 0x%x\n",
+	   vf->abs_vfid, q->sp_obj.func_id, q->cid);
 }
 
 /* called by bnx2x_nic_load */
 int bnx2x_iov_nic_init(struct bnx2x *bp)
 {
-	int vfid, qcount, i;
+	int vfid;
 
 	if (!IS_SRIOV(bp)) {
 		DP(BNX2X_MSG_IOV, "vfdb was not allocated\n");
@@ -2155,7 +2162,7 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 		   BNX2X_FIRST_VF_CID + base_vf_cid, base_cxt);
 
 		/* init statically provisioned resources */
-		bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+		bnx2x_iov_static_resc(bp, vf);
 
 		/* queues are initialized during VF-ACQUIRE */
 
@@ -2191,13 +2198,12 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 	}
 
 	/* Final VF init */
-	qcount = 0;
-	for_each_vf(bp, i) {
-		struct bnx2x_virtf *vf = BP_VF(bp, i);
+	for_each_vf(bp, vfid) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vfid);
 
 		/* fill in the BDF and bars */
-		vf->bus = bnx2x_vf_bus(bp, i);
-		vf->devfn = bnx2x_vf_devfn(bp, i);
+		vf->bus = bnx2x_vf_bus(bp, vfid);
+		vf->devfn = bnx2x_vf_devfn(bp, vfid);
 		bnx2x_vf_set_bars(bp, vf);
 
 		DP(BNX2X_MSG_IOV,
@@ -2206,10 +2212,6 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 		   (unsigned)vf->bars[0].bar, vf->bars[0].size,
 		   (unsigned)vf->bars[1].bar, vf->bars[1].size,
 		   (unsigned)vf->bars[2].bar, vf->bars[2].size);
-
-		/* set local queue arrays */
-		vf->vfqs = &bp->vfdb->vfqs[qcount];
-		qcount += bnx2x_vf(bp, i, alloc_resc.num_sbs);
 	}
 
 	return 0;
@@ -2515,6 +2517,9 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 		for_each_vfq(vf, j) {
 			struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
 
+			dma_addr_t q_stats_addr =
+				vf->fw_stat_map + j * vf->stats_stride;
+
 			/* collect stats fro active queues only */
 			if (bnx2x_get_q_logical_state(bp, &rxq->sp_obj) ==
 			    BNX2X_Q_LOGICAL_STATE_STOPPED)
@@ -2522,13 +2527,13 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 
 			/* create stats query entry for this queue */
 			cur_query_entry->kind = STATS_TYPE_QUEUE;
-			cur_query_entry->index = vfq_cl_id(vf, rxq);
+			cur_query_entry->index = vfq_stat_id(vf, rxq);
 			cur_query_entry->funcID =
 				cpu_to_le16(FW_VF_HANDLE(vf->abs_vfid));
 			cur_query_entry->address.hi =
-				cpu_to_le32(U64_HI(vf->fw_stat_map));
+				cpu_to_le32(U64_HI(q_stats_addr));
 			cur_query_entry->address.lo =
-				cpu_to_le32(U64_LO(vf->fw_stat_map));
+				cpu_to_le32(U64_LO(q_stats_addr));
 			DP(BNX2X_MSG_IOV,
 			   "added address %x %x for vf %d queue %d client %d\n",
 			   cur_query_entry->address.hi,
@@ -2537,6 +2542,10 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 			cur_query_entry++;
 			cur_data_offset += sizeof(struct per_queue_stats);
 			stats_count++;
+
+			/* all stats are coalesced to the leading queue */
+			if (vf->cfg_flags & VF_CFG_STATS_COALESCE)
+				break;
 		}
 	}
 	bp->fw_stats_req->hdr.cmd_num = bp->fw_stats_num + stats_count;
@@ -2555,6 +2564,11 @@ void bnx2x_iov_sp_task(struct bnx2x *bp)
 	for_each_vf(bp, i) {
 		struct bnx2x_virtf *vf = BP_VF(bp, i);
 
+		if (!vf) {
+			BNX2X_ERR("VF was null! skipping...\n");
+			continue;
+		}
+
 		if (!list_empty(&vf->op_list_head) &&
 		    atomic_read(&vf->op_in_progress)) {
 			DP(BNX2X_MSG_IOV, "running pending op for vf %d\n", i);
@@ -2702,7 +2716,7 @@ int bnx2x_vf_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		struct bnx2x_vf_queue *q = vfq_get(vf, i);
 
 		if (!q) {
-			DP(BNX2X_MSG_IOV, "q number %d was not allocated\n", i);
+			BNX2X_ERR("q number %d was not allocated\n", i);
 			return -EINVAL;
 		}
 
@@ -2930,6 +2944,43 @@ op_done:
 	bnx2x_vfop_end(bp, vf, vfop);
 }
 
+static void bnx2x_vfop_rss(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	enum bnx2x_vfop_rss_state state;
+
+	if (!vfop) {
+		BNX2X_ERR("vfop was null\n");
+		return;
+	}
+
+	state = vfop->state;
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_RSS_CONFIG:
+		/* next state */
+		vfop->state = BNX2X_VFOP_RSS_DONE;
+		bnx2x_config_rss(bp, &vfop->op_p->rss);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+op_err:
+		BNX2X_ERR("RSS error: rc %d\n", vfop->rc);
+op_done:
+	case BNX2X_VFOP_RSS_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_pending:
+	return;
+}
+
 int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 			   struct bnx2x_virtf *vf,
 			   struct bnx2x_vfop_cmd *cmd)
@@ -2944,6 +2995,21 @@ int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 	return -ENOMEM;
 }
 
+int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
+		       struct bnx2x_virtf *vf,
+		       struct bnx2x_vfop_cmd *cmd)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		bnx2x_vfop_opset(BNX2X_VFOP_RSS_CONFIG, bnx2x_vfop_rss,
+				 cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_rss,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
+
 /* VF release ~ VF close + VF release-resources
  * Release is the ultimate SW shutdown and is called whenever an
  * irrecoverable error is encountered.
@@ -2955,6 +3021,8 @@ void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block)
 		.block = block,
 	};
 	int rc;
+
+	DP(BNX2X_MSG_IOV, "PF releasing vf %d\n", vf->abs_vfid);
 	bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
 
 	rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
@@ -2983,6 +3051,12 @@ static inline void bnx2x_vf_get_bars(struct bnx2x *bp, struct bnx2x_virtf *vf,
 void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			      enum channel_tlvs tlv)
 {
+	/* we don't lock the channel for unsupported tlvs */
+	if (!bnx2x_tlv_supported(tlv)) {
+		BNX2X_ERR("attempting to lock with unsupported tlv. Aborting\n");
+		return;
+	}
+
 	/* lock the channel */
 	mutex_lock(&vf->op_mutex);
 
@@ -2997,19 +3071,32 @@ void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 void bnx2x_unlock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				enum channel_tlvs expected_tlv)
 {
+	enum channel_tlvs current_tlv;
+
+	if (!vf) {
+		BNX2X_ERR("VF was %p\n", vf);
+		return;
+	}
+
+	current_tlv = vf->op_current;
+
+	/* we don't unlock the channel for unsupported tlvs */
+	if (!bnx2x_tlv_supported(expected_tlv))
+		return;
+
 	WARN(expected_tlv != vf->op_current,
 	     "lock mismatch: expected %d found %d", expected_tlv,
 	     vf->op_current);
 
+	/* record the locking op */
+	vf->op_current = CHANNEL_TLV_NONE;
+
 	/* lock the channel */
 	mutex_unlock(&vf->op_mutex);
 
 	/* log the unlock */
 	DP(BNX2X_MSG_IOV, "VF[%d]: vf pf channel unlocked by %d\n",
 	   vf->abs_vfid, vf->op_current);
-
-	/* record the locking op */
-	vf->op_current = CHANNEL_TLV_NONE;
 }
 
 int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs_param)
@@ -3040,11 +3127,77 @@ int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs_param)
 		return bnx2x_enable_sriov(bp);
 	}
 }
+#define IGU_ENTRY_SIZE 4
 
 int bnx2x_enable_sriov(struct bnx2x *bp)
 {
 	int rc = 0, req_vfs = bp->requested_nr_virtfn;
+	int vf_idx, sb_idx, vfq_idx, qcount, first_vf;
+	u32 igu_entry, address;
+	u16 num_vf_queues;
+
+	if (req_vfs == 0)
+		return 0;
+
+	first_vf = bp->vfdb->sriov.first_vf_in_pf;
+
+	/* statically distribute vf sb pool between VFs */
+	num_vf_queues = min_t(u16, BNX2X_VF_MAX_QUEUES,
+			      BP_VFDB(bp)->vf_sbs_pool / req_vfs);
+
+	/* zero previous values learned from igu cam */
+	for (vf_idx = 0; vf_idx < req_vfs; vf_idx++) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
+
+		vf->sb_count = 0;
+		vf_sb_count(BP_VF(bp, vf_idx)) = 0;
+	}
+	bp->vfdb->vf_sbs_pool = 0;
+
+	/* prepare IGU cam */
+	sb_idx = BP_VFDB(bp)->first_vf_igu_entry;
+	address = IGU_REG_MAPPING_MEMORY + sb_idx * IGU_ENTRY_SIZE;
+	for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
+		for (vfq_idx = 0; vfq_idx < num_vf_queues; vfq_idx++) {
+			igu_entry = vf_idx << IGU_REG_MAPPING_MEMORY_FID_SHIFT |
+				vfq_idx << IGU_REG_MAPPING_MEMORY_VECTOR_SHIFT |
+				IGU_REG_MAPPING_MEMORY_VALID;
+			DP(BNX2X_MSG_IOV, "assigning sb %d to vf %d\n",
+			   sb_idx, vf_idx);
+			REG_WR(bp, address, igu_entry);
+			sb_idx++;
+			address += IGU_ENTRY_SIZE;
+		}
+	}
+
+	/* Reinitialize vf database according to igu cam */
+	bnx2x_get_vf_igu_cam_info(bp);
+
+	DP(BNX2X_MSG_IOV, "vf_sbs_pool %d, num_vf_queues %d\n",
+	   BP_VFDB(bp)->vf_sbs_pool, num_vf_queues);
+
+	qcount = 0;
+	for_each_vf(bp, vf_idx) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
+
+		/* set local queue arrays */
+		vf->vfqs = &bp->vfdb->vfqs[qcount];
+		qcount += vf_sb_count(vf);
+	}
 
+	/* prepare msix vectors in VF configuration space */
+	for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
+		bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf_idx));
+		REG_WR(bp, PCICFG_OFFSET + GRC_CONFIG_REG_VF_MSIX_CONTROL,
+		       num_vf_queues);
+	}
+	bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
+
+	/* enable sriov. This will probe all the VFs, and consequentially cause
+	 * the "acquire" messages to appear on the VF PF channel.
+	 */
+	DP(BNX2X_MSG_IOV, "about to call enable sriov\n");
+	pci_disable_sriov(bp->pdev);
 	rc = pci_enable_sriov(bp->pdev, req_vfs);
 	if (rc) {
 		BNX2X_ERR("pci_enable_sriov failed with %d\n", rc);
@@ -3072,9 +3225,8 @@ void bnx2x_disable_sriov(struct bnx2x *bp)
 	pci_disable_sriov(bp->pdev);
 }
 
-static int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx,
-			     struct bnx2x_virtf **vf,
-			     struct pf_vf_bulletin_content **bulletin)
+int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx, struct bnx2x_virtf **vf,
+			struct pf_vf_bulletin_content **bulletin)
 {
 	if (bp->state != BNX2X_STATE_OPEN) {
 		BNX2X_ERR("vf ndo called though PF is down\n");
@@ -3097,7 +3249,13 @@ static int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx,
 	*bulletin = BP_VF_BULLETIN(bp, vfidx);
 
 	if (!*vf) {
-		BNX2X_ERR("vf ndo called but vf was null. vfidx was %d\n",
+		BNX2X_ERR("vf ndo called but vf struct is null. vfidx was %d\n",
+			  vfidx);
+		return -EINVAL;
+	}
+
+	if (!(*vf)->vfqs) {
+		BNX2X_ERR("vf ndo called but vfqs struct is null. Was ndo invoked before dynamically enabling SR-IOV? vfidx was %d\n",
 			  vfidx);
 		return -EINVAL;
 	}
@@ -3125,8 +3283,8 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 	rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
 	if (rc)
 		return rc;
-	mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
-	vlan_obj = &bnx2x_vfq(vf, 0, vlan_obj);
+	mac_obj = &bnx2x_leading_vfq(vf, mac_obj);
+	vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
 	if (!mac_obj || !vlan_obj) {
 		BNX2X_ERR("VF partially initialized\n");
 		return -EINVAL;
@@ -3138,10 +3296,13 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 	ivi->spoofchk = 1; /*always enabled */
 	if (vf->state == VF_ENABLED) {
 		/* mac and vlan are in vlan_mac objects */
-		mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
-					0, ETH_ALEN);
-		vlan_obj->get_n_elements(bp, vlan_obj, 1, (u8 *)&ivi->vlan,
-					 0, VLAN_HLEN);
+		if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj)))
+			mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
+						0, ETH_ALEN);
+		if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, vlan_obj)))
+			vlan_obj->get_n_elements(bp, vlan_obj, 1,
+						 (u8 *)&ivi->vlan, 0,
+						 VLAN_HLEN);
 	} else {
 		/* mac */
 		if (bulletin->valid_bitmap & (1 << MAC_ADDR_VALID))
@@ -3209,14 +3370,18 @@ int bnx2x_set_vf_mac(struct net_device *dev, int vfidx, u8 *mac)
 		return rc;
 	}
 
-	/* is vf initialized and queue set up? */
 	q_logical_state =
-		bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+		bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
 	if (vf->state == VF_ENABLED &&
 	    q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
 		/* configure the mac in device on this vf's queue */
 		unsigned long ramrod_flags = 0;
-		struct bnx2x_vlan_mac_obj *mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
+		struct bnx2x_vlan_mac_obj *mac_obj =
+			&bnx2x_leading_vfq(vf, mac_obj);
+
+		rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+		if (rc)
+			return rc;
 
 		/* must lock vfpf channel to protect against vf flows */
 		bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
@@ -3276,18 +3441,21 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 
 	/* is vf initialized and queue set up? */
 	q_logical_state =
-		bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+		bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
 	if (vf->state == VF_ENABLED &&
 	    q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
 		/* configure the vlan in device on this vf's queue */
 		unsigned long ramrod_flags = 0;
 		unsigned long vlan_mac_flags = 0;
 		struct bnx2x_vlan_mac_obj *vlan_obj =
-			&bnx2x_vfq(vf, 0, vlan_obj);
+			&bnx2x_leading_vfq(vf, vlan_obj);
 		struct bnx2x_vlan_mac_ramrod_params ramrod_param;
 		struct bnx2x_queue_state_params q_params = {NULL};
 		struct bnx2x_queue_update_params *update_params;
 
+		rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+		if (rc)
+			return rc;
 		memset(&ramrod_param, 0, sizeof(ramrod_param));
 
 		/* must lock vfpf channel to protect against vf flows */
@@ -3307,7 +3475,7 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 		 */
 		__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
 		q_params.cmd = BNX2X_Q_CMD_UPDATE;
-		q_params.q_obj = &bnx2x_vfq(vf, 0, sp_obj);
+		q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
 		update_params = &q_params.params.update;
 		__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
 			  &update_params->update_flags);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h

@@ -81,6 +81,7 @@ struct bnx2x_vf_queue {
 	u32 cid;
 	u16 index;
 	u16 sb_idx;
+	bool is_leading;
 };
 
 /* struct bnx2x_vfop_qctor_params - prepare queue construction parameters:
@@ -194,6 +195,7 @@ struct bnx2x_virtf {
 #define VF_CFG_INT_SIMD		0x0008
 #define VF_CACHE_LINE		0x0010
 #define VF_CFG_VLAN		0x0020
+#define VF_CFG_STATS_COALESCE	0x0040
 
 	u8 state;
 #define VF_FREE		0	/* VF ready to be acquired holds no resc */
@@ -213,6 +215,7 @@ struct bnx2x_virtf {
 
 	/* dma */
 	dma_addr_t fw_stat_map;		/* valid iff VF_CFG_STATS */
+	u16 stats_stride;
 	dma_addr_t spq_map;
 	dma_addr_t bulletin_map;
 
@@ -239,7 +242,10 @@ struct bnx2x_virtf {
 	u8 igu_base_id;	/* base igu status block id */
 
 	struct bnx2x_vf_queue	*vfqs;
-#define bnx2x_vfq(vf, nr, var)	((vf)->vfqs[(nr)].var)
+#define LEADING_IDX			0
+#define bnx2x_vfq_is_leading(vfq)	((vfq)->index == LEADING_IDX)
+#define bnx2x_vfq(vf, nr, var)		((vf)->vfqs[(nr)].var)
+#define bnx2x_leading_vfq(vf, var)	((vf)->vfqs[LEADING_IDX].var)
 
 	u8 index;	/* index in the vf array */
 	u8 abs_vfid;
@@ -358,6 +364,10 @@ struct bnx2x_vf_sp {
 		struct client_init_ramrod_data  init_data;
 		struct client_update_ramrod_data update_data;
 	} q_data;
+
+	union {
+		struct eth_rss_update_ramrod_data e2;
+	} rss_rdata;
 };
 
 struct hw_dma {
@@ -403,6 +413,10 @@ struct bnx2x_vfdb {
 
 #define FLRD_VFS_DWORDS (BNX2X_MAX_NUM_OF_VFS / 32)
 	u32 flrd_vfs[FLRD_VFS_DWORDS];
+
+	/* the number of msix vectors belonging to this PF designated for VFs */
+	u16 vf_sbs_pool;
+	u16 first_vf_igu_entry;
 };
 
 /* queue access */
@@ -411,11 +425,6 @@ static inline struct bnx2x_vf_queue *vfq_get(struct bnx2x_virtf *vf, u8 index)
 	return &(vf->vfqs[index]);
 }
 
-static inline bool vfq_is_leading(struct bnx2x_vf_queue *vfq)
-{
-	return (vfq->index == 0);
-}
-
 /* FW ids */
 static inline u8 vf_igu_sb(struct bnx2x_virtf *vf, u16 sb_idx)
 {
@@ -434,7 +443,10 @@ static u8 vfq_cl_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
 
 static inline u8 vfq_stat_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
 {
-	return vfq_cl_id(vf, q);
+	if (vf->cfg_flags & VF_CFG_STATS_COALESCE)
+		return vf->leading_rss;
+	else
+		return vfq_cl_id(vf, q);
 }
 
 static inline u8 vfq_qzone_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
@@ -691,6 +703,10 @@ int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 			   struct bnx2x_virtf *vf,
 			   struct bnx2x_vfop_cmd *cmd);
 
+int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
+		       struct bnx2x_virtf *vf,
+		       struct bnx2x_vfop_cmd *cmd);
+
 /* VF release ~ VF close + VF release-resources
  *
  * Release is the ultimate SW shutdown and is called whenever an
@@ -730,9 +746,12 @@ int bnx2x_vfpf_release(struct bnx2x *bp);
 int bnx2x_vfpf_release(struct bnx2x *bp);
 int bnx2x_vfpf_init(struct bnx2x *bp);
 void bnx2x_vfpf_close_vf(struct bnx2x *bp);
-int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx);
+int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp,
+		       bool is_leading);
 int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx);
 int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set);
+int bnx2x_vfpf_config_rss(struct bnx2x *bp,
+			  struct bnx2x_config_rss_params *params);
 int bnx2x_vfpf_set_mcast(struct net_device *dev);
 int bnx2x_vfpf_storm_rx_mode(struct bnx2x *bp);
 
@@ -758,7 +777,7 @@ int bnx2x_enable_sriov(struct bnx2x *bp);
 void bnx2x_disable_sriov(struct bnx2x *bp);
 static inline int bnx2x_vf_headroom(struct bnx2x *bp)
 {
-	return bp->vfdb->sriov.nr_virtfn * BNX2X_CLIENTS_PER_VF;
+	return bp->vfdb->sriov.nr_virtfn * BNX2X_CIDS_PER_VF;
 }
 void bnx2x_pf_set_vfs_vlan(struct bnx2x *bp);
 int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs);
@@ -793,7 +812,7 @@ static inline int bnx2x_vfpf_acquire(struct bnx2x *bp,
 static inline int bnx2x_vfpf_release(struct bnx2x *bp) {return 0; }
 static inline int bnx2x_vfpf_init(struct bnx2x *bp) {return 0; }
 static inline void bnx2x_vfpf_close_vf(struct bnx2x *bp) {}
-static inline int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx) {return 0; }
+static inline int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bool is_leading) {return 0; }
 static inline int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx) {return 0; }
 static inline int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr,
 					u8 vf_qid, bool set) {return 0; }

drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c

@@ -257,17 +257,23 @@ int bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count)
 
 			/* humble our request */
 			req->resc_request.num_txqs =
-				bp->acquire_resp.resc.num_txqs;
+				min(req->resc_request.num_txqs,
+				    bp->acquire_resp.resc.num_txqs);
 			req->resc_request.num_rxqs =
-				bp->acquire_resp.resc.num_rxqs;
+				min(req->resc_request.num_rxqs,
+				    bp->acquire_resp.resc.num_rxqs);
 			req->resc_request.num_sbs =
-				bp->acquire_resp.resc.num_sbs;
+				min(req->resc_request.num_sbs,
+				    bp->acquire_resp.resc.num_sbs);
 			req->resc_request.num_mac_filters =
-				bp->acquire_resp.resc.num_mac_filters;
+				min(req->resc_request.num_mac_filters,
+				    bp->acquire_resp.resc.num_mac_filters);
 			req->resc_request.num_vlan_filters =
-				bp->acquire_resp.resc.num_vlan_filters;
+				min(req->resc_request.num_vlan_filters,
+				    bp->acquire_resp.resc.num_vlan_filters);
 			req->resc_request.num_mc_filters =
-				bp->acquire_resp.resc.num_mc_filters;
+				min(req->resc_request.num_mc_filters,
+				    bp->acquire_resp.resc.num_mc_filters);
 
 			/* Clear response buffer */
 			memset(&bp->vf2pf_mbox->resp, 0,
@@ -293,7 +299,7 @@ int bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count)
 	bp->common.flash_size = 0;
 	bp->flags |=
 		NO_WOL_FLAG | NO_ISCSI_OOO_FLAG | NO_ISCSI_FLAG | NO_FCOE_FLAG;
-	bp->igu_sb_cnt = 1;
+	bp->igu_sb_cnt = bp->acquire_resp.resc.num_sbs;
 	bp->igu_base_sb = bp->acquire_resp.resc.hw_sbs[0].hw_sb_id;
 	strlcpy(bp->fw_ver, bp->acquire_resp.pfdev_info.fw_ver,
 		sizeof(bp->fw_ver));
@@ -373,6 +379,8 @@ int bnx2x_vfpf_init(struct bnx2x *bp)
 	req->stats_addr = bp->fw_stats_data_mapping +
 			  offsetof(struct bnx2x_fw_stats_data, queue_stats);
 
+	req->stats_stride = sizeof(struct per_queue_stats);
+
 	/* add list termination tlv */
 	bnx2x_add_tlv(bp, req, req->first_tlv.tl.length, CHANNEL_TLV_LIST_END,
 		      sizeof(struct channel_list_end_tlv));
@@ -452,12 +460,60 @@ free_irq:
 	bnx2x_free_irq(bp);
 }
 
+static void bnx2x_leading_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				   struct bnx2x_vf_queue *q)
+{
+	u8 cl_id = vfq_cl_id(vf, q);
+	u8 func_id = FW_VF_HANDLE(vf->abs_vfid);
+
+	/* mac */
+	bnx2x_init_mac_obj(bp, &q->mac_obj,
+			   cl_id, q->cid, func_id,
+			   bnx2x_vf_sp(bp, vf, mac_rdata),
+			   bnx2x_vf_sp_map(bp, vf, mac_rdata),
+			   BNX2X_FILTER_MAC_PENDING,
+			   &vf->filter_state,
+			   BNX2X_OBJ_TYPE_RX_TX,
+			   &bp->macs_pool);
+	/* vlan */
+	bnx2x_init_vlan_obj(bp, &q->vlan_obj,
+			    cl_id, q->cid, func_id,
+			    bnx2x_vf_sp(bp, vf, vlan_rdata),
+			    bnx2x_vf_sp_map(bp, vf, vlan_rdata),
+			    BNX2X_FILTER_VLAN_PENDING,
+			    &vf->filter_state,
+			    BNX2X_OBJ_TYPE_RX_TX,
+			    &bp->vlans_pool);
+
+	/* mcast */
+	bnx2x_init_mcast_obj(bp, &vf->mcast_obj, cl_id,
+			     q->cid, func_id, func_id,
+			     bnx2x_vf_sp(bp, vf, mcast_rdata),
+			     bnx2x_vf_sp_map(bp, vf, mcast_rdata),
+			     BNX2X_FILTER_MCAST_PENDING,
+			     &vf->filter_state,
+			     BNX2X_OBJ_TYPE_RX_TX);
+
+	/* rss */
+	bnx2x_init_rss_config_obj(bp, &vf->rss_conf_obj, cl_id, q->cid,
+				  func_id, func_id,
+				  bnx2x_vf_sp(bp, vf, rss_rdata),
+				  bnx2x_vf_sp_map(bp, vf, rss_rdata),
+				  BNX2X_FILTER_RSS_CONF_PENDING,
+				  &vf->filter_state,
+				  BNX2X_OBJ_TYPE_RX_TX);
+
+	vf->leading_rss = cl_id;
+	q->is_leading = true;
+}
+
 /* ask the pf to open a queue for the vf */
-int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx)
+int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp,
+		       bool is_leading)
 {
 	struct vfpf_setup_q_tlv *req = &bp->vf2pf_mbox->req.setup_q;
 	struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
-	struct bnx2x_fastpath *fp = &bp->fp[fp_idx];
+	u8 fp_idx = fp->index;
 	u16 tpa_agg_size = 0, flags = 0;
 	int rc;
 
@@ -473,6 +529,9 @@ int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx)
 		tpa_agg_size = TPA_AGG_SIZE;
 	}
 
+	if (is_leading)
+		flags |= VFPF_QUEUE_FLG_LEADING_RSS;
+
 	/* calculate queue flags */
 	flags |= VFPF_QUEUE_FLG_STATS;
 	flags |= VFPF_QUEUE_FLG_CACHE_ALIGN;
@@ -646,6 +705,71 @@ out:
 	return 0;
 }
 
+/* request pf to config rss table for vf queues*/
+int bnx2x_vfpf_config_rss(struct bnx2x *bp,
+			  struct bnx2x_config_rss_params *params)
+{
+	struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
+	struct vfpf_rss_tlv *req = &bp->vf2pf_mbox->req.update_rss;
+	int rc = 0;
+
+	/* clear mailbox and prep first tlv */
+	bnx2x_vfpf_prep(bp, &req->first_tlv, CHANNEL_TLV_UPDATE_RSS,
+			sizeof(*req));
+
+	/* add list termination tlv */
+	bnx2x_add_tlv(bp, req, req->first_tlv.tl.length, CHANNEL_TLV_LIST_END,
+		      sizeof(struct channel_list_end_tlv));
+
+	memcpy(req->ind_table, params->ind_table, T_ETH_INDIRECTION_TABLE_SIZE);
+	memcpy(req->rss_key, params->rss_key, sizeof(params->rss_key));
+	req->ind_table_size = T_ETH_INDIRECTION_TABLE_SIZE;
+	req->rss_key_size = T_ETH_RSS_KEY;
+	req->rss_result_mask = params->rss_result_mask;
+
+	/* flags handled individually for backward/forward compatability */
+	if (params->rss_flags & (1 << BNX2X_RSS_MODE_DISABLED))
+		req->rss_flags |= VFPF_RSS_MODE_DISABLED;
+	if (params->rss_flags & (1 << BNX2X_RSS_MODE_REGULAR))
+		req->rss_flags |= VFPF_RSS_MODE_REGULAR;
+	if (params->rss_flags & (1 << BNX2X_RSS_SET_SRCH))
+		req->rss_flags |= VFPF_RSS_SET_SRCH;
+	if (params->rss_flags & (1 << BNX2X_RSS_IPV4))
+		req->rss_flags |= VFPF_RSS_IPV4;
+	if (params->rss_flags & (1 << BNX2X_RSS_IPV4_TCP))
+		req->rss_flags |= VFPF_RSS_IPV4_TCP;
+	if (params->rss_flags & (1 << BNX2X_RSS_IPV4_UDP))
+		req->rss_flags |= VFPF_RSS_IPV4_UDP;
+	if (params->rss_flags & (1 << BNX2X_RSS_IPV6))
+		req->rss_flags |= VFPF_RSS_IPV6;
+	if (params->rss_flags & (1 << BNX2X_RSS_IPV6_TCP))
+		req->rss_flags |= VFPF_RSS_IPV6_TCP;
+	if (params->rss_flags & (1 << BNX2X_RSS_IPV6_UDP))
+		req->rss_flags |= VFPF_RSS_IPV6_UDP;
+
+	DP(BNX2X_MSG_IOV, "rss flags %x\n", req->rss_flags);
+
+	/* output tlvs list */
+	bnx2x_dp_tlv_list(bp, req);
+
+	/* send message to pf */
+	rc = bnx2x_send_msg2pf(bp, &resp->hdr.status, bp->vf2pf_mbox_mapping);
+	if (rc) {
+		BNX2X_ERR("failed to send message to pf. rc was %d\n", rc);
+		goto out;
+	}
+
+	if (resp->hdr.status != PFVF_STATUS_SUCCESS) {
+		BNX2X_ERR("failed to send rss message to PF over Vf PF channel %d\n",
+			  resp->hdr.status);
+		rc = -EINVAL;
+	}
+out:
+	bnx2x_vfpf_finalize(bp, &req->first_tlv);
+
+	return 0;
+}
+
 int bnx2x_vfpf_set_mcast(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
@@ -948,7 +1072,7 @@ static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf,
 
 	/* fill in pfdev info */
 	resp->pfdev_info.chip_num = bp->common.chip_id;
-	resp->pfdev_info.db_size = (1 << BNX2X_DB_SHIFT);
+	resp->pfdev_info.db_size = bp->db_size;
 	resp->pfdev_info.indices_per_sb = HC_SB_MAX_INDICES_E2;
 	resp->pfdev_info.pf_cap = (PFVF_CAP_RSS |
 				   /* PFVF_CAP_DHC |*/ PFVF_CAP_TPA);
@@ -1054,8 +1178,13 @@ static void bnx2x_vf_mbx_init_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	/* record ghost addresses from vf message */
 	vf->spq_map = init->spq_addr;
 	vf->fw_stat_map = init->stats_addr;
+	vf->stats_stride = init->stats_stride;
 	vf->op_rc = bnx2x_vf_init(bp, vf, (dma_addr_t *)init->sb_addr);
 
+	/* set VF multiqueue statistics collection mode */
+	if (init->flags & VFPF_INIT_FLG_STATS_COALESCE)
+		vf->cfg_flags |= VF_CFG_STATS_COALESCE;
+
 	/* response */
 	bnx2x_vf_mbx_resp(bp, vf);
 }
@@ -1080,6 +1209,8 @@ static void bnx2x_vf_mbx_set_q_flags(struct bnx2x *bp, u32 mbx_q_flags,
 		__set_bit(BNX2X_Q_FLG_HC, sp_q_flags);
 	if (mbx_q_flags & VFPF_QUEUE_FLG_DHC)
 		__set_bit(BNX2X_Q_FLG_DHC, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_LEADING_RSS)
+		__set_bit(BNX2X_Q_FLG_LEADING_RSS, sp_q_flags);
 
 	/* outer vlan removal is set according to PF's multi function mode */
 	if (IS_MF_SD(bp))
@@ -1113,6 +1244,9 @@ static void bnx2x_vf_mbx_setup_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		struct bnx2x_queue_init_params *init_p;
 		struct bnx2x_queue_setup_params *setup_p;
 
+		if (bnx2x_vfq_is_leading(q))
+			bnx2x_leading_vfq_init(bp, vf, q);
+
 		/* re-init the VF operation context */
 		memset(&vf->op_params.qctor, 0 , sizeof(vf->op_params.qctor));
 		setup_p = &vf->op_params.qctor.prep_qsetup;
@@ -1552,6 +1686,68 @@ static void bnx2x_vf_mbx_release_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		bnx2x_vf_mbx_resp(bp, vf);
 }
 
+static void bnx2x_vf_mbx_update_rss(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				    struct bnx2x_vf_mbx *mbx)
+{
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_resp,
+		.block = false,
+	};
+	struct bnx2x_config_rss_params *vf_op_params = &vf->op_params.rss;
+	struct vfpf_rss_tlv *rss_tlv = &mbx->msg->req.update_rss;
+
+	if (rss_tlv->ind_table_size != T_ETH_INDIRECTION_TABLE_SIZE ||
+	    rss_tlv->rss_key_size != T_ETH_RSS_KEY) {
+		BNX2X_ERR("failing rss configuration of vf %d due to size mismatch\n",
+			  vf->index);
+		vf->op_rc = -EINVAL;
+		goto mbx_resp;
+	}
+
+	/* set vfop params according to rss tlv */
+	memcpy(vf_op_params->ind_table, rss_tlv->ind_table,
+	       T_ETH_INDIRECTION_TABLE_SIZE);
+	memcpy(vf_op_params->rss_key, rss_tlv->rss_key,
+	       sizeof(rss_tlv->rss_key));
+	vf_op_params->rss_obj = &vf->rss_conf_obj;
+	vf_op_params->rss_result_mask = rss_tlv->rss_result_mask;
+
+	/* flags handled individually for backward/forward compatability */
+	if (rss_tlv->rss_flags & VFPF_RSS_MODE_DISABLED)
+		__set_bit(BNX2X_RSS_MODE_DISABLED, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_MODE_REGULAR)
+		__set_bit(BNX2X_RSS_MODE_REGULAR, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_SET_SRCH)
+		__set_bit(BNX2X_RSS_SET_SRCH, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV4)
+		__set_bit(BNX2X_RSS_IPV4, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV4_TCP)
+		__set_bit(BNX2X_RSS_IPV4_TCP, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV4_UDP)
+		__set_bit(BNX2X_RSS_IPV4_UDP, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV6)
+		__set_bit(BNX2X_RSS_IPV6, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV6_TCP)
+		__set_bit(BNX2X_RSS_IPV6_TCP, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV6_UDP)
+		__set_bit(BNX2X_RSS_IPV6_UDP, &vf_op_params->rss_flags);
+
+	if ((!(rss_tlv->rss_flags & VFPF_RSS_IPV4_TCP) &&
+	     rss_tlv->rss_flags & VFPF_RSS_IPV4_UDP) ||
+	    (!(rss_tlv->rss_flags & VFPF_RSS_IPV6_TCP) &&
+	     rss_tlv->rss_flags & VFPF_RSS_IPV6_UDP)) {
+		BNX2X_ERR("about to hit a FW assert. aborting...\n");
+		vf->op_rc = -EINVAL;
+		goto mbx_resp;
+	}
+
+	vf->op_rc = bnx2x_vfop_rss_cmd(bp, vf, &cmd);
+
+mbx_resp:
+	if (vf->op_rc)
+		bnx2x_vf_mbx_resp(bp, vf);
+}
+
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -1588,6 +1784,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_RELEASE:
 			bnx2x_vf_mbx_release_vf(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_UPDATE_RSS:
+			bnx2x_vf_mbx_update_rss(bp, vf, mbx);
+			break;
 		}
 
 	} else {
@@ -1607,7 +1806,7 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		/* test whether we can respond to the VF (do we have an address
 		 * for it?)
 		 */
-		if (vf->state == VF_ACQUIRED) {
+		if (vf->state == VF_ACQUIRED || vf->state == VF_ENABLED) {
 			/* mbx_resp uses the op_rc of the VF */
 			vf->op_rc = PFVF_STATUS_NOT_SUPPORTED;
 

drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h

@@ -51,6 +51,7 @@ struct hw_sb_info {
 #define VFPF_QUEUE_FLG_COS		0x0080
 #define VFPF_QUEUE_FLG_HC		0x0100
 #define VFPF_QUEUE_FLG_DHC		0x0200
+#define VFPF_QUEUE_FLG_LEADING_RSS	0x0400
 
 #define VFPF_QUEUE_DROP_IP_CS_ERR	(1 << 0)
 #define VFPF_QUEUE_DROP_TCP_CS_ERR	(1 << 1)
@@ -131,6 +132,27 @@ struct vfpf_q_op_tlv {
 	u8 padding[3];
 };
 
+/* receive side scaling tlv */
+struct vfpf_rss_tlv {
+	struct vfpf_first_tlv	first_tlv;
+	u32			rss_flags;
+#define VFPF_RSS_MODE_DISABLED	(1 << 0)
+#define VFPF_RSS_MODE_REGULAR	(1 << 1)
+#define VFPF_RSS_SET_SRCH	(1 << 2)
+#define VFPF_RSS_IPV4		(1 << 3)
+#define VFPF_RSS_IPV4_TCP	(1 << 4)
+#define VFPF_RSS_IPV4_UDP	(1 << 5)
+#define VFPF_RSS_IPV6		(1 << 6)
+#define VFPF_RSS_IPV6_TCP	(1 << 7)
+#define VFPF_RSS_IPV6_UDP	(1 << 8)
+	u8			rss_result_mask;
+	u8			ind_table_size;
+	u8			rss_key_size;
+	u8			padding;
+	u8			ind_table[T_ETH_INDIRECTION_TABLE_SIZE];
+	u32			rss_key[T_ETH_RSS_KEY];	/* hash values */
+};
+
 /* acquire response tlv - carries the allocated resources */
 struct pfvf_acquire_resp_tlv {
 	struct pfvf_tlv hdr;
@@ -166,12 +188,20 @@ struct pfvf_acquire_resp_tlv {
 	} resc;
 };
 
+#define VFPF_INIT_FLG_STATS_COALESCE	(1 << 0) /* when set the VFs queues
+						  * stats will be coalesced on
+						  * the leading RSS queue
+						  */
+
 /* Init VF */
 struct vfpf_init_tlv {
 	struct vfpf_first_tlv first_tlv;
 	aligned_u64 sb_addr[PFVF_MAX_SBS_PER_VF]; /* vf_sb based */
 	aligned_u64 spq_addr;
 	aligned_u64 stats_addr;
+	u16 stats_stride;
+	u32 flags;
+	u32 padding[2];
 };
 
 /* Setup Queue */
@@ -293,13 +323,14 @@ union vfpf_tlvs {
 	struct vfpf_q_op_tlv		q_op;
 	struct vfpf_setup_q_tlv		setup_q;
 	struct vfpf_set_q_filters_tlv	set_q_filters;
-	struct vfpf_release_tlv         release;
-	struct channel_list_end_tlv     list_end;
+	struct vfpf_release_tlv		release;
+	struct vfpf_rss_tlv		update_rss;
+	struct channel_list_end_tlv	list_end;
 	struct tlv_buffer_size		tlv_buf_size;
 };
 
 union pfvf_tlvs {
-	struct pfvf_general_resp_tlv    general_resp;
+	struct pfvf_general_resp_tlv	general_resp;
 	struct pfvf_acquire_resp_tlv	acquire_resp;
 	struct channel_list_end_tlv	list_end;
 	struct tlv_buffer_size		tlv_buf_size;
@@ -355,14 +386,18 @@ enum channel_tlvs {
 	CHANNEL_TLV_INIT,
 	CHANNEL_TLV_SETUP_Q,
 	CHANNEL_TLV_SET_Q_FILTERS,
+	CHANNEL_TLV_ACTIVATE_Q,
+	CHANNEL_TLV_DEACTIVATE_Q,
 	CHANNEL_TLV_TEARDOWN_Q,
 	CHANNEL_TLV_CLOSE,
 	CHANNEL_TLV_RELEASE,
+	CHANNEL_TLV_UPDATE_RSS_DEPRECATED,
 	CHANNEL_TLV_PF_RELEASE_VF,
 	CHANNEL_TLV_LIST_END,
 	CHANNEL_TLV_FLR,
 	CHANNEL_TLV_PF_SET_MAC,
 	CHANNEL_TLV_PF_SET_VLAN,
+	CHANNEL_TLV_UPDATE_RSS,
 	CHANNEL_TLV_MAX
 };
 

drivers/net/ethernet/broadcom/cnic.c

@@ -1,6 +1,6 @@
 /* cnic.c: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2012 Broadcom Corporation
+ * Copyright (c) 2006-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -1184,6 +1184,7 @@ error:
 static int cnic_alloc_bnx2x_context(struct cnic_dev *dev)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	int ctx_blk_size = cp->ethdev->ctx_blk_size;
 	int total_mem, blks, i;
 
@@ -1201,7 +1202,7 @@ static int cnic_alloc_bnx2x_context(struct cnic_dev *dev)
 
 	cp->ctx_blks = blks;
 	cp->ctx_blk_size = ctx_blk_size;
-	if (!BNX2X_CHIP_IS_57710(cp->chip_id))
+	if (!CHIP_IS_E1(bp))
 		cp->ctx_align = 0;
 	else
 		cp->ctx_align = ctx_blk_size;
@@ -1231,6 +1232,7 @@ static int cnic_alloc_bnx2x_context(struct cnic_dev *dev)
 static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_eth_dev *ethdev = cp->ethdev;
 	u32 start_cid = ethdev->starting_cid;
 	int i, j, n, ret, pages;
@@ -1240,7 +1242,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 	cp->iscsi_start_cid = start_cid;
 	cp->fcoe_start_cid = start_cid + MAX_ISCSI_TBL_SZ;
 
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp)) {
 		cp->max_cid_space += dev->max_fcoe_conn;
 		cp->fcoe_init_cid = ethdev->fcoe_init_cid;
 		if (!cp->fcoe_init_cid)
@@ -1288,7 +1290,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 	if (ret)
 		goto error;
 
-	if (CNIC_SUPPORTS_FCOE(cp)) {
+	if (CNIC_SUPPORTS_FCOE(bp)) {
 		ret = cnic_alloc_kcq(dev, &cp->kcq2, true);
 		if (ret)
 			goto error;
@@ -1382,6 +1384,7 @@ static int cnic_submit_kwqe_16(struct cnic_dev *dev, u32 cmd, u32 cid,
 				u32 type, union l5cm_specific_data *l5_data)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct l5cm_spe kwqe;
 	struct kwqe_16 *kwq[1];
 	u16 type_16;
@@ -1389,10 +1392,10 @@ static int cnic_submit_kwqe_16(struct cnic_dev *dev, u32 cmd, u32 cid,
 
 	kwqe.hdr.conn_and_cmd_data =
 		cpu_to_le32(((cmd << SPE_HDR_CMD_ID_SHIFT) |
-			     BNX2X_HW_CID(cp, cid)));
+			     BNX2X_HW_CID(bp, cid)));
 
 	type_16 = (type << SPE_HDR_CONN_TYPE_SHIFT) & SPE_HDR_CONN_TYPE;
-	type_16 |= (cp->pfid << SPE_HDR_FUNCTION_ID_SHIFT) &
+	type_16 |= (bp->pfid << SPE_HDR_FUNCTION_ID_SHIFT) &
 		   SPE_HDR_FUNCTION_ID;
 
 	kwqe.hdr.type = cpu_to_le16(type_16);
@@ -1427,13 +1430,34 @@ static void cnic_reply_bnx2x_kcqes(struct cnic_dev *dev, int ulp_type,
 	rcu_read_unlock();
 }
 
+static void cnic_bnx2x_set_tcp_options(struct cnic_dev *dev, int time_stamps,
+				       int en_tcp_dack)
+{
+	struct bnx2x *bp = netdev_priv(dev->netdev);
+	u8 xstorm_flags = XSTORM_L5CM_TCP_FLAGS_WND_SCL_EN;
+	u16 tstorm_flags = 0;
+
+	if (time_stamps) {
+		xstorm_flags |= XSTORM_L5CM_TCP_FLAGS_TS_ENABLED;
+		tstorm_flags |= TSTORM_L5CM_TCP_FLAGS_TS_ENABLED;
+	}
+	if (en_tcp_dack)
+		tstorm_flags |= TSTORM_L5CM_TCP_FLAGS_DELAYED_ACK_EN;
+
+	CNIC_WR8(dev, BAR_XSTRORM_INTMEM +
+		 XSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(bp->pfid), xstorm_flags);
+
+	CNIC_WR16(dev, BAR_TSTRORM_INTMEM +
+		  TSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(bp->pfid), tstorm_flags);
+}
+
 static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe)
 {
 	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct iscsi_kwqe_init1 *req1 = (struct iscsi_kwqe_init1 *) kwqe;
 	int hq_bds, pages;
-	u32 pfid = cp->pfid;
+	u32 pfid = bp->pfid;
 
 	cp->num_iscsi_tasks = req1->num_tasks_per_conn;
 	cp->num_ccells = req1->num_ccells_per_conn;
@@ -1506,15 +1530,18 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe)
 	CNIC_WR16(dev, BAR_CSTRORM_INTMEM + CSTORM_ISCSI_HQ_SIZE_OFFSET(pfid),
 		  hq_bds);
 
+	cnic_bnx2x_set_tcp_options(dev,
+			req1->flags & ISCSI_KWQE_INIT1_TIME_STAMPS_ENABLE,
+			req1->flags & ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE);
+
 	return 0;
 }
 
 static int cnic_bnx2x_iscsi_init2(struct cnic_dev *dev, struct kwqe *kwqe)
 {
 	struct iscsi_kwqe_init2 *req2 = (struct iscsi_kwqe_init2 *) kwqe;
-	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
-	u32 pfid = cp->pfid;
+	u32 pfid = bp->pfid;
 	struct iscsi_kcqe kcqe;
 	struct kcqe *cqes[1];
 
@@ -1653,6 +1680,7 @@ static int cnic_setup_bnx2x_ctx(struct cnic_dev *dev, struct kwqe *wqes[],
 				u32 num)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct iscsi_kwqe_conn_offload1 *req1 =
 			(struct iscsi_kwqe_conn_offload1 *) wqes[0];
 	struct iscsi_kwqe_conn_offload2 *req2 =
@@ -1661,11 +1689,11 @@ static int cnic_setup_bnx2x_ctx(struct cnic_dev *dev, struct kwqe *wqes[],
 	struct cnic_context *ctx = &cp->ctx_tbl[req1->iscsi_conn_id];
 	struct cnic_iscsi *iscsi = ctx->proto.iscsi;
 	u32 cid = ctx->cid;
-	u32 hw_cid = BNX2X_HW_CID(cp, cid);
+	u32 hw_cid = BNX2X_HW_CID(bp, cid);
 	struct iscsi_context *ictx;
 	struct regpair context_addr;
 	int i, j, n = 2, n_max;
-	u8 port = CNIC_PORT(cp);
+	u8 port = BP_PORT(bp);
 
 	ctx->ctx_flags = 0;
 	if (!req2->num_additional_wqes)
@@ -1719,8 +1747,8 @@ static int cnic_setup_bnx2x_ctx(struct cnic_dev *dev, struct kwqe *wqes[],
 		XSTORM_ISCSI_CONTEXT_FLAGS_B_INITIAL_R2T;
 	ictx->xstorm_st_context.common.ethernet.reserved_vlan_type =
 		ETH_P_8021Q;
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) &&
-		cp->port_mode == CHIP_2_PORT_MODE) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp) &&
+	    bp->common.chip_port_mode == CHIP_2_PORT_MODE) {
 
 		port = 0;
 	}
@@ -1841,6 +1869,7 @@ static int cnic_bnx2x_iscsi_ofld1(struct cnic_dev *dev, struct kwqe *wqes[],
 	struct iscsi_kwqe_conn_offload1 *req1;
 	struct iscsi_kwqe_conn_offload2 *req2;
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_context *ctx;
 	struct iscsi_kcqe kcqe;
 	struct kcqe *cqes[1];
@@ -1894,7 +1923,7 @@ static int cnic_bnx2x_iscsi_ofld1(struct cnic_dev *dev, struct kwqe *wqes[],
 	}
 
 	kcqe.completion_status = ISCSI_KCQE_COMPLETION_STATUS_SUCCESS;
-	kcqe.iscsi_conn_context_id = BNX2X_HW_CID(cp, cp->ctx_tbl[l5_cid].cid);
+	kcqe.iscsi_conn_context_id = BNX2X_HW_CID(bp, cp->ctx_tbl[l5_cid].cid);
 
 done:
 	cqes[0] = (struct kcqe *) &kcqe;
@@ -1930,6 +1959,7 @@ static int cnic_bnx2x_iscsi_update(struct cnic_dev *dev, struct kwqe *kwqe)
 static int cnic_bnx2x_destroy_ramrod(struct cnic_dev *dev, u32 l5_cid)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_context *ctx = &cp->ctx_tbl[l5_cid];
 	union l5cm_specific_data l5_data;
 	int ret;
@@ -1938,7 +1968,7 @@ static int cnic_bnx2x_destroy_ramrod(struct cnic_dev *dev, u32 l5_cid)
 	init_waitqueue_head(&ctx->waitq);
 	ctx->wait_cond = 0;
 	memset(&l5_data, 0, sizeof(l5_data));
-	hw_cid = BNX2X_HW_CID(cp, ctx->cid);
+	hw_cid = BNX2X_HW_CID(bp, ctx->cid);
 
 	ret = cnic_submit_kwqe_16(dev, RAMROD_CMD_ID_COMMON_CFC_DEL,
 				  hw_cid, NONE_CONNECTION_TYPE, &l5_data);
@@ -2035,9 +2065,6 @@ static void cnic_init_storm_conn_bufs(struct cnic_dev *dev,
 	xstorm_buf->pseudo_header_checksum =
 		swab16(~csum_ipv6_magic(&src_ip, &dst_ip, 0, IPPROTO_TCP, 0));
 
-	if (!(kwqe1->tcp_flags & L4_KWQ_CONNECT_REQ1_NO_DELAY_ACK))
-		tstorm_buf->params |=
-			L5CM_TSTORM_CONN_BUFFER_DELAYED_ACK_ENABLE;
 	if (kwqe3->ka_timeout) {
 		tstorm_buf->ka_enable = 1;
 		tstorm_buf->ka_timeout = kwqe3->ka_timeout;
@@ -2049,9 +2076,8 @@ static void cnic_init_storm_conn_bufs(struct cnic_dev *dev,
 
 static void cnic_init_bnx2x_mac(struct cnic_dev *dev)
 {
-	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
-	u32 pfid = cp->pfid;
+	u32 pfid = bp->pfid;
 	u8 *mac = dev->mac_addr;
 
 	CNIC_WR8(dev, BAR_XSTRORM_INTMEM +
@@ -2084,25 +2110,6 @@ static void cnic_init_bnx2x_mac(struct cnic_dev *dev)
 		 mac[0]);
 }
 
-static void cnic_bnx2x_set_tcp_timestamp(struct cnic_dev *dev, int tcp_ts)
-{
-	struct cnic_local *cp = dev->cnic_priv;
-	struct bnx2x *bp = netdev_priv(dev->netdev);
-	u8 xstorm_flags = XSTORM_L5CM_TCP_FLAGS_WND_SCL_EN;
-	u16 tstorm_flags = 0;
-
-	if (tcp_ts) {
-		xstorm_flags |= XSTORM_L5CM_TCP_FLAGS_TS_ENABLED;
-		tstorm_flags |= TSTORM_L5CM_TCP_FLAGS_TS_ENABLED;
-	}
-
-	CNIC_WR8(dev, BAR_XSTRORM_INTMEM +
-		 XSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(cp->pfid), xstorm_flags);
-
-	CNIC_WR16(dev, BAR_TSTRORM_INTMEM +
-		  TSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(cp->pfid), tstorm_flags);
-}
-
 static int cnic_bnx2x_connect(struct cnic_dev *dev, struct kwqe *wqes[],
 			      u32 num, int *work)
 {
@@ -2176,10 +2183,7 @@ static int cnic_bnx2x_connect(struct cnic_dev *dev, struct kwqe *wqes[],
 	cnic_init_storm_conn_bufs(dev, kwqe1, kwqe3, conn_buf);
 
 	CNIC_WR16(dev, BAR_XSTRORM_INTMEM +
-		  XSTORM_ISCSI_LOCAL_VLAN_OFFSET(cp->pfid), csk->vlan_id);
-
-	cnic_bnx2x_set_tcp_timestamp(dev,
-		kwqe1->tcp_flags & L4_KWQ_CONNECT_REQ1_TIME_STAMP);
+		  XSTORM_ISCSI_LOCAL_VLAN_OFFSET(bp->pfid), csk->vlan_id);
 
 	ret = cnic_submit_kwqe_16(dev, L5CM_RAMROD_CMD_ID_TCP_CONNECT,
 			kwqe1->cid, ISCSI_CONNECTION_TYPE, &l5_data);
@@ -2248,11 +2252,12 @@ static int cnic_bnx2x_fcoe_stat(struct cnic_dev *dev, struct kwqe *kwqe)
 	struct fcoe_stat_ramrod_params *fcoe_stat;
 	union l5cm_specific_data l5_data;
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	int ret;
 	u32 cid;
 
 	req = (struct fcoe_kwqe_stat *) kwqe;
-	cid = BNX2X_HW_CID(cp, cp->fcoe_init_cid);
+	cid = BNX2X_HW_CID(bp, cp->fcoe_init_cid);
 
 	fcoe_stat = cnic_get_kwqe_16_data(cp, BNX2X_FCOE_L5_CID_BASE, &l5_data);
 	if (!fcoe_stat)
@@ -2271,6 +2276,7 @@ static int cnic_bnx2x_fcoe_init1(struct cnic_dev *dev, struct kwqe *wqes[],
 {
 	int ret;
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	u32 cid;
 	struct fcoe_init_ramrod_params *fcoe_init;
 	struct fcoe_kwqe_init1 *req1;
@@ -2315,7 +2321,7 @@ static int cnic_bnx2x_fcoe_init1(struct cnic_dev *dev, struct kwqe *wqes[],
 	fcoe_init->sb_id = HC_INDEX_FCOE_EQ_CONS;
 	cp->kcq2.sw_prod_idx = 0;
 
-	cid = BNX2X_HW_CID(cp, cp->fcoe_init_cid);
+	cid = BNX2X_HW_CID(bp, cp->fcoe_init_cid);
 	ret = cnic_submit_kwqe_16(dev, FCOE_RAMROD_CMD_ID_INIT_FUNC, cid,
 				  FCOE_CONNECTION_TYPE, &l5_data);
 	*work = 3;
@@ -2328,6 +2334,7 @@ static int cnic_bnx2x_fcoe_ofld1(struct cnic_dev *dev, struct kwqe *wqes[],
 	int ret = 0;
 	u32 cid = -1, l5_cid;
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct fcoe_kwqe_conn_offload1 *req1;
 	struct fcoe_kwqe_conn_offload2 *req2;
 	struct fcoe_kwqe_conn_offload3 *req3;
@@ -2370,7 +2377,7 @@ static int cnic_bnx2x_fcoe_ofld1(struct cnic_dev *dev, struct kwqe *wqes[],
 
 	fctx = cnic_get_bnx2x_ctx(dev, cid, 1, &ctx_addr);
 	if (fctx) {
-		u32 hw_cid = BNX2X_HW_CID(cp, cid);
+		u32 hw_cid = BNX2X_HW_CID(bp, cid);
 		u32 val;
 
 		val = CDU_RSRVD_VALUE_TYPE_A(hw_cid, CDU_REGION_NUMBER_XCM_AG,
@@ -2394,7 +2401,7 @@ static int cnic_bnx2x_fcoe_ofld1(struct cnic_dev *dev, struct kwqe *wqes[],
 	memcpy(&fcoe_offload->offload_kwqe3, req3, sizeof(*req3));
 	memcpy(&fcoe_offload->offload_kwqe4, req4, sizeof(*req4));
 
-	cid = BNX2X_HW_CID(cp, cid);
+	cid = BNX2X_HW_CID(bp, cid);
 	ret = cnic_submit_kwqe_16(dev, FCOE_RAMROD_CMD_ID_OFFLOAD_CONN, cid,
 				  FCOE_CONNECTION_TYPE, &l5_data);
 	if (!ret)
@@ -2552,13 +2559,14 @@ static int cnic_bnx2x_fcoe_fw_destroy(struct cnic_dev *dev, struct kwqe *kwqe)
 	struct fcoe_kwqe_destroy *req;
 	union l5cm_specific_data l5_data;
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	int ret;
 	u32 cid;
 
 	cnic_bnx2x_delete_wait(dev, MAX_ISCSI_TBL_SZ);
 
 	req = (struct fcoe_kwqe_destroy *) kwqe;
-	cid = BNX2X_HW_CID(cp, cp->fcoe_init_cid);
+	cid = BNX2X_HW_CID(bp, cp->fcoe_init_cid);
 
 	memset(&l5_data, 0, sizeof(l5_data));
 	ret = cnic_submit_kwqe_16(dev, FCOE_RAMROD_CMD_ID_DESTROY_FUNC, cid,
@@ -2715,7 +2723,7 @@ static int cnic_submit_bnx2x_iscsi_kwqes(struct cnic_dev *dev,
 static int cnic_submit_bnx2x_fcoe_kwqes(struct cnic_dev *dev,
 					struct kwqe *wqes[], u32 num_wqes)
 {
-	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	int i, work, ret;
 	u32 opcode;
 	struct kwqe *kwqe;
@@ -2723,7 +2731,7 @@ static int cnic_submit_bnx2x_fcoe_kwqes(struct cnic_dev *dev,
 	if (!test_bit(CNIC_F_CNIC_UP, &dev->flags))
 		return -EAGAIN;		/* bnx2 is down */
 
-	if (!BNX2X_CHIP_IS_E2_PLUS(cp->chip_id))
+	if (!BNX2X_CHIP_IS_E2_PLUS(bp))
 		return -EINVAL;
 
 	for (i = 0; i < num_wqes; ) {
@@ -3039,8 +3047,8 @@ static irqreturn_t cnic_irq(int irq, void *dev_instance)
 static inline void cnic_ack_bnx2x_int(struct cnic_dev *dev, u8 id, u8 storm,
 				      u16 index, u8 op, u8 update)
 {
-	struct cnic_local *cp = dev->cnic_priv;
-	u32 hc_addr = (HC_REG_COMMAND_REG + CNIC_PORT(cp) * 32 +
+	struct bnx2x *bp = netdev_priv(dev->netdev);
+	u32 hc_addr = (HC_REG_COMMAND_REG + BP_PORT(bp) * 32 +
 		       COMMAND_REG_INT_ACK);
 	struct igu_ack_register igu_ack;
 
@@ -3603,6 +3611,7 @@ static int cnic_cm_create(struct cnic_dev *dev, int ulp_type, u32 cid,
 	csk1->rcv_buf = DEF_RCV_BUF;
 	csk1->snd_buf = DEF_SND_BUF;
 	csk1->seed = DEF_SEED;
+	csk1->tcp_flags = 0;
 
 	*csk = csk1;
 	return 0;
@@ -4020,15 +4029,18 @@ static void cnic_cm_process_kcqe(struct cnic_dev *dev, struct kcqe *kcqe)
 		cnic_cm_upcall(cp, csk, opcode);
 		break;
 
-	case L5CM_RAMROD_CMD_ID_CLOSE:
-		if (l4kcqe->status != 0) {
-			netdev_warn(dev->netdev, "RAMROD CLOSE compl with "
-				    "status 0x%x\n", l4kcqe->status);
+	case L5CM_RAMROD_CMD_ID_CLOSE: {
+		struct iscsi_kcqe *l5kcqe = (struct iscsi_kcqe *) kcqe;
+
+		if (l4kcqe->status != 0 || l5kcqe->completion_status != 0) {
+			netdev_warn(dev->netdev, "RAMROD CLOSE compl with status 0x%x completion status 0x%x\n",
+				    l4kcqe->status, l5kcqe->completion_status);
 			opcode = L4_KCQE_OPCODE_VALUE_CLOSE_COMP;
 			/* Fall through */
 		} else {
 			break;
 		}
+	}
 	case L4_KCQE_OPCODE_VALUE_RESET_RECEIVED:
 	case L4_KCQE_OPCODE_VALUE_CLOSE_COMP:
 	case L4_KCQE_OPCODE_VALUE_RESET_COMP:
@@ -4213,13 +4225,12 @@ static void cnic_cm_stop_bnx2x_hw(struct cnic_dev *dev)
 
 static int cnic_cm_init_bnx2x_hw(struct cnic_dev *dev)
 {
-	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
-	u32 pfid = cp->pfid;
-	u32 port = CNIC_PORT(cp);
+	u32 pfid = bp->pfid;
+	u32 port = BP_PORT(bp);
 
 	cnic_init_bnx2x_mac(dev);
-	cnic_bnx2x_set_tcp_timestamp(dev, 1);
+	cnic_bnx2x_set_tcp_options(dev, 0, 1);
 
 	CNIC_WR16(dev, BAR_XSTRORM_INTMEM +
 		  XSTORM_ISCSI_LOCAL_VLAN_OFFSET(pfid), 0);
@@ -4897,6 +4908,7 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev,
 				    struct client_init_ramrod_data *data)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_uio_dev *udev = cp->udev;
 	union eth_tx_bd_types *txbd = (union eth_tx_bd_types *) udev->l2_ring;
 	dma_addr_t buf_map, ring_map = udev->l2_ring_map;
@@ -4925,7 +4937,7 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev,
 		start_bd->general_data &= ~ETH_TX_START_BD_PARSE_NBDS;
 		start_bd->general_data |= (1 << ETH_TX_START_BD_HDR_NBDS_SHIFT);
 
-		if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id))
+		if (BNX2X_CHIP_IS_E2_PLUS(bp))
 			pbd_e2->parsing_data = (UNICAST_ADDRESS <<
 				ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE_SHIFT);
 		else
@@ -4962,6 +4974,7 @@ static void cnic_init_bnx2x_rx_ring(struct cnic_dev *dev,
 				    struct client_init_ramrod_data *data)
 {
 	struct cnic_local *cp = dev->cnic_priv;
+	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_uio_dev *udev = cp->udev;
 	struct eth_rx_bd *rxbd = (struct eth_rx_bd *) (udev->l2_ring +
 				BNX2_PAGE_SIZE);
@@ -4970,7 +4983,7 @@ static void cnic_init_bnx2x_rx_ring(struct cnic_dev *dev,
 	struct host_sp_status_block *sb = cp->bnx2x_def_status_blk;
 	int i;
 	u32 cli = cp->ethdev->iscsi_l2_client_id;
-	int cl_qzone_id = BNX2X_CL_QZONE_ID(cp, cli);
+	int cl_qzone_id = BNX2X_CL_QZONE_ID(bp, cli);
 	u32 val;
 	dma_addr_t ring_map = udev->l2_ring_map;
 
@@ -4979,7 +4992,7 @@ static void cnic_init_bnx2x_rx_ring(struct cnic_dev *dev,
 	data->general.activate_flg = 1;
 	data->general.sp_client_id = cli;
 	data->general.mtu = cpu_to_le16(cp->l2_single_buf_size - 14);
-	data->general.func_id = cp->pfid;
+	data->general.func_id = bp->pfid;
 
 	for (i = 0; i < BNX2X_MAX_RX_DESC_CNT; i++, rxbd++) {
 		dma_addr_t buf_map;
@@ -5029,13 +5042,13 @@ static void cnic_init_bnx2x_kcq(struct cnic_dev *dev)
 {
 	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
-	u32 pfid = cp->pfid;
+	u32 pfid = bp->pfid;
 
 	cp->kcq1.io_addr = BAR_CSTRORM_INTMEM +
 			   CSTORM_ISCSI_EQ_PROD_OFFSET(pfid, 0);
 	cp->kcq1.sw_prod_idx = 0;
 
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp)) {
 		struct host_hc_status_block_e2 *sb = cp->status_blk.gen;
 
 		cp->kcq1.hw_prod_idx_ptr =
@@ -5051,7 +5064,7 @@ static void cnic_init_bnx2x_kcq(struct cnic_dev *dev)
 			&sb->sb.running_index[SM_RX_ID];
 	}
 
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp)) {
 		struct host_hc_status_block_e2 *sb = cp->status_blk.gen;
 
 		cp->kcq2.io_addr = BAR_USTRORM_INTMEM +
@@ -5073,12 +5086,10 @@ static int cnic_start_bnx2x_hw(struct cnic_dev *dev)
 	u32 pfid;
 
 	dev->stats_addr = ethdev->addr_drv_info_to_mcp;
-	cp->port_mode = bp->common.chip_port_mode;
-	cp->pfid = bp->pfid;
 	cp->func = bp->pf_num;
 
 	func = CNIC_FUNC(cp);
-	pfid = cp->pfid;
+	pfid = bp->pfid;
 
 	ret = cnic_init_id_tbl(&cp->cid_tbl, MAX_ISCSI_TBL_SZ,
 			       cp->iscsi_start_cid, 0);
@@ -5086,7 +5097,7 @@ static int cnic_start_bnx2x_hw(struct cnic_dev *dev)
 	if (ret)
 		return -ENOMEM;
 
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp)) {
 		ret = cnic_init_id_tbl(&cp->fcoe_cid_tbl, dev->max_fcoe_conn,
 					cp->fcoe_start_cid, 0);
 
@@ -5168,12 +5179,12 @@ static void cnic_init_rings(struct cnic_dev *dev)
 		rx_prods.cqe_prod = BNX2X_MAX_RCQ_DESC_CNT;
 		barrier();
 
-		cl_qzone_id = BNX2X_CL_QZONE_ID(cp, cli);
+		cl_qzone_id = BNX2X_CL_QZONE_ID(bp, cli);
 
 		off = BAR_USTRORM_INTMEM +
-			(BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) ?
+			(BNX2X_CHIP_IS_E2_PLUS(bp) ?
 			 USTORM_RX_PRODS_E2_OFFSET(cl_qzone_id) :
-			 USTORM_RX_PRODS_E1X_OFFSET(CNIC_PORT(cp), cli));
+			 USTORM_RX_PRODS_E1X_OFFSET(BP_PORT(bp), cli));
 
 		for (i = 0; i < sizeof(struct ustorm_eth_rx_producers) / 4; i++)
 			CNIC_WR(dev, off + i * 4, ((u32 *) &rx_prods)[i]);
@@ -5271,6 +5282,13 @@ static int cnic_register_netdev(struct cnic_dev *dev)
 	if (err)
 		netdev_err(dev->netdev, "register_cnic failed\n");
 
+	/* Read iSCSI config again.  On some bnx2x device, iSCSI config
+	 * can change after firmware is downloaded.
+	 */
+	dev->max_iscsi_conn = ethdev->max_iscsi_conn;
+	if (ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI)
+		dev->max_iscsi_conn = 0;
+
 	return err;
 }
 
@@ -5353,7 +5371,7 @@ static void cnic_stop_bnx2x_hw(struct cnic_dev *dev)
 
 	cnic_free_irq(dev);
 
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp)) {
 		idx_off = offsetof(struct hc_status_block_e2, index_values) +
 			  (hc_index * sizeof(u16));
 
@@ -5370,7 +5388,7 @@ static void cnic_stop_bnx2x_hw(struct cnic_dev *dev)
 
 	*cp->kcq1.hw_prod_idx_ptr = 0;
 	CNIC_WR(dev, BAR_CSTRORM_INTMEM +
-		CSTORM_ISCSI_EQ_CONS_OFFSET(cp->pfid, 0), 0);
+		CSTORM_ISCSI_EQ_CONS_OFFSET(bp->pfid, 0), 0);
 	CNIC_WR16(dev, cp->kcq1.io_addr, 0);
 	cnic_free_resc(dev);
 }
@@ -5544,7 +5562,7 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev)
 
 	if (!(ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI))
 		cdev->max_iscsi_conn = ethdev->max_iscsi_conn;
-	if (CNIC_SUPPORTS_FCOE(cp)) {
+	if (CNIC_SUPPORTS_FCOE(bp)) {
 		cdev->max_fcoe_conn = ethdev->max_fcoe_conn;
 		cdev->max_fcoe_exchanges = ethdev->max_fcoe_exchanges;
 	}
@@ -5564,7 +5582,7 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev)
 	cp->stop_cm = cnic_cm_stop_bnx2x_hw;
 	cp->enable_int = cnic_enable_bnx2x_int;
 	cp->disable_int_sync = cnic_disable_bnx2x_int_sync;
-	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) {
+	if (BNX2X_CHIP_IS_E2_PLUS(bp)) {
 		cp->ack_int = cnic_ack_bnx2x_e2_msix;
 		cp->arm_int = cnic_arm_bnx2x_e2_msix;
 	} else {
@@ -5628,7 +5646,7 @@ static int cnic_netdev_event(struct notifier_block *this, unsigned long event,
 
 	dev = cnic_from_netdev(netdev);
 
-	if (!dev && (event == NETDEV_REGISTER || netif_running(netdev))) {
+	if (!dev && event == NETDEV_REGISTER) {
 		/* Check for the hot-plug device */
 		dev = is_cnic_dev(netdev);
 		if (dev) {
@@ -5644,7 +5662,7 @@ static int cnic_netdev_event(struct notifier_block *this, unsigned long event,
 		else if (event == NETDEV_UNREGISTER)
 			cnic_ulp_exit(dev);
 
-		if (event == NETDEV_UP || (new_dev && netif_running(netdev))) {
+		if (event == NETDEV_UP) {
 			if (cnic_register_netdev(dev) != 0) {
 				cnic_put(dev);
 				goto done;
@@ -5693,21 +5711,8 @@ static struct notifier_block cnic_netdev_notifier = {
 
 static void cnic_release(void)
 {
-	struct cnic_dev *dev;
 	struct cnic_uio_dev *udev;
 
-	while (!list_empty(&cnic_dev_list)) {
-		dev = list_entry(cnic_dev_list.next, struct cnic_dev, list);
-		if (test_bit(CNIC_F_CNIC_UP, &dev->flags)) {
-			cnic_ulp_stop(dev);
-			cnic_stop_hw(dev);
-		}
-
-		cnic_ulp_exit(dev);
-		cnic_unregister_netdev(dev);
-		list_del_init(&dev->list);
-		cnic_free_dev(dev);
-	}
 	while (!list_empty(&cnic_udev_list)) {
 		udev = list_entry(cnic_udev_list.next, struct cnic_uio_dev,
 				  list);

drivers/net/ethernet/broadcom/cnic.h

@@ -1,6 +1,6 @@
 /* cnic.h: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2011 Broadcom Corporation
+ * Copyright (c) 2006-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -303,8 +303,6 @@ struct cnic_local {
 
 	u32			chip_id;
 	int			func;
-	u32			pfid;
-	u8			port_mode;
 
 	u32			shmem_base;
 
@@ -364,47 +362,7 @@ struct bnx2x_bd_chain_next {
 
 #define BNX2X_FCOE_L5_CID_BASE		MAX_ISCSI_TBL_SZ
 
-#define BNX2X_CHIP_NUM_57710		0x164e
-#define BNX2X_CHIP_NUM_57711		0x164f
-#define BNX2X_CHIP_NUM_57711E		0x1650
-#define BNX2X_CHIP_NUM_57712		0x1662
-#define BNX2X_CHIP_NUM_57712E		0x1663
-#define BNX2X_CHIP_NUM_57713		0x1651
-#define BNX2X_CHIP_NUM_57713E		0x1652
-#define BNX2X_CHIP_NUM_57800		0x168a
-#define BNX2X_CHIP_NUM_57810		0x168e
-#define BNX2X_CHIP_NUM_57840		0x168d
-
-#define BNX2X_CHIP_NUM(x)		(x >> 16)
-#define BNX2X_CHIP_IS_57710(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57710)
-#define BNX2X_CHIP_IS_57711(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57711)
-#define BNX2X_CHIP_IS_57711E(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57711E)
-#define BNX2X_CHIP_IS_E1H(x)		\
-	(BNX2X_CHIP_IS_57711(x) || BNX2X_CHIP_IS_57711E(x))
-#define BNX2X_CHIP_IS_57712(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57712)
-#define BNX2X_CHIP_IS_57712E(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57712E)
-#define BNX2X_CHIP_IS_57713(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57713)
-#define BNX2X_CHIP_IS_57713E(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57713E)
-#define BNX2X_CHIP_IS_57800(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57800)
-#define BNX2X_CHIP_IS_57810(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57810)
-#define BNX2X_CHIP_IS_57840(x)		\
-	(BNX2X_CHIP_NUM(x) == BNX2X_CHIP_NUM_57840)
-#define BNX2X_CHIP_IS_E2(x)		\
-	(BNX2X_CHIP_IS_57712(x) || BNX2X_CHIP_IS_57712E(x) || \
-	 BNX2X_CHIP_IS_57713(x) || BNX2X_CHIP_IS_57713E(x))
-#define BNX2X_CHIP_IS_E3(x)			\
-	(BNX2X_CHIP_IS_57800(x) || BNX2X_CHIP_IS_57810(x) || \
-	 BNX2X_CHIP_IS_57840(x))
-#define BNX2X_CHIP_IS_E2_PLUS(x) (BNX2X_CHIP_IS_E2(x) || BNX2X_CHIP_IS_E3(x))
+#define BNX2X_CHIP_IS_E2_PLUS(bp) (CHIP_IS_E2(bp) || CHIP_IS_E3(bp))
 
 #define BNX2X_RX_DESC_CNT		(BNX2_PAGE_SIZE / \
 					 sizeof(struct eth_rx_bd))
@@ -439,31 +397,26 @@ struct bnx2x_bd_chain_next {
 #define ETH_MAX_RX_CLIENTS_E2 		ETH_MAX_RX_CLIENTS_E1H
 #endif
 
-#define CNIC_PORT(cp)			((cp)->pfid & 1)
 #define CNIC_FUNC(cp)			((cp)->func)
-#define CNIC_PATH(cp)			(!BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) ? \
-					 0 : (CNIC_FUNC(cp) & 1))
-#define CNIC_E1HVN(cp)			((cp)->pfid >> 1)
 
-#define BNX2X_HW_CID(cp, x)		((CNIC_PORT(cp) << 23) | \
-					 (CNIC_E1HVN(cp) << 17) | (x))
+#define BNX2X_HW_CID(bp, x)		((BP_PORT(bp) << 23) | \
+					 (BP_VN(bp) << 17) | (x))
 
 #define BNX2X_SW_CID(x)			(x & 0x1ffff)
 
-#define BNX2X_CL_QZONE_ID(cp, cli)					\
-		(BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) ? cli :		\
-		 cli + (CNIC_PORT(cp) * ETH_MAX_RX_CLIENTS_E1H))
+#define BNX2X_CL_QZONE_ID(bp, cli)					\
+		(BNX2X_CHIP_IS_E2_PLUS(bp) ? cli :			\
+		 cli + (BP_PORT(bp) * ETH_MAX_RX_CLIENTS_E1H))
 
 #ifndef MAX_STAT_COUNTER_ID
 #define MAX_STAT_COUNTER_ID						\
-	(BNX2X_CHIP_IS_E1H((cp)->chip_id) ? MAX_STAT_COUNTER_ID_E1H :	\
-	 ((BNX2X_CHIP_IS_E2_PLUS((cp)->chip_id)) ? MAX_STAT_COUNTER_ID_E2 :\
+	(CHIP_IS_E1H(bp) ? MAX_STAT_COUNTER_ID_E1H :			\
+	 ((BNX2X_CHIP_IS_E2_PLUS(bp)) ? MAX_STAT_COUNTER_ID_E2 :	\
 	  MAX_STAT_COUNTER_ID_E1))
 #endif
 
-#define CNIC_SUPPORTS_FCOE(cp)					\
-	(BNX2X_CHIP_IS_E2_PLUS((cp)->chip_id) &&		\
-	 !((cp)->ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE))
+#define CNIC_SUPPORTS_FCOE(cp)						\
+	(BNX2X_CHIP_IS_E2_PLUS(bp) && !NO_FCOE(bp))
 
 #define CNIC_RAMROD_TMO			(HZ / 4)
 

drivers/net/ethernet/broadcom/cnic_defs.h

@@ -1,7 +1,7 @@
 
 /* cnic.c: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2012 Broadcom Corporation
+ * Copyright (c) 2006-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -5400,8 +5400,8 @@ struct tstorm_l5cm_tcp_flags {
 	u16 flags;
 #define TSTORM_L5CM_TCP_FLAGS_VLAN_ID (0xFFF<<0)
 #define TSTORM_L5CM_TCP_FLAGS_VLAN_ID_SHIFT 0
-#define TSTORM_L5CM_TCP_FLAGS_RSRV0 (0x1<<12)
-#define TSTORM_L5CM_TCP_FLAGS_RSRV0_SHIFT 12
+#define TSTORM_L5CM_TCP_FLAGS_DELAYED_ACK_EN (0x1<<12)
+#define TSTORM_L5CM_TCP_FLAGS_DELAYED_ACK_SHIFT 12
 #define TSTORM_L5CM_TCP_FLAGS_TS_ENABLED (0x1<<13)
 #define TSTORM_L5CM_TCP_FLAGS_TS_ENABLED_SHIFT 13
 #define TSTORM_L5CM_TCP_FLAGS_RSRV1 (0x3<<14)

drivers/net/ethernet/broadcom/cnic_if.h

@@ -1,6 +1,6 @@
 /* cnic_if.h: Broadcom CNIC core network driver.
  *
- * Copyright (c) 2006-2012 Broadcom Corporation
+ * Copyright (c) 2006-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -14,8 +14,8 @@
 
 #include "bnx2x/bnx2x_mfw_req.h"
 
-#define CNIC_MODULE_VERSION	"2.5.16"
-#define CNIC_MODULE_RELDATE	"Dec 05, 2012"
+#define CNIC_MODULE_VERSION	"2.5.18"
+#define CNIC_MODULE_RELDATE	"Sept 01, 2013"
 
 #define CNIC_ULP_RDMA		0
 #define CNIC_ULP_ISCSI		1
@@ -238,8 +238,8 @@ struct cnic_sock {
 	u16	src_port;
 	u16	dst_port;
 	u16	vlan_id;
-	unsigned char old_ha[6];
-	unsigned char ha[6];
+	unsigned char old_ha[ETH_ALEN];
+	unsigned char ha[ETH_ALEN];
 	u32	mtu;
 	u32	cid;
 	u32	l5_cid;
@@ -308,7 +308,7 @@ struct cnic_dev {
 #define CNIC_F_BNX2_CLASS	3
 #define CNIC_F_BNX2X_CLASS	4
 	atomic_t	ref_count;
-	u8		mac_addr[6];
+	u8		mac_addr[ETH_ALEN];
 
 	int		max_iscsi_conn;
 	int		max_fcoe_conn;

drivers/net/ethernet/broadcom/tg3.c

@@ -94,10 +94,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 
 #define DRV_MODULE_NAME		"tg3"
 #define TG3_MAJ_NUM			3
-#define TG3_MIN_NUM			132
+#define TG3_MIN_NUM			133
 #define DRV_MODULE_VERSION	\
 	__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE	"May 21, 2013"
+#define DRV_MODULE_RELDATE	"Jul 29, 2013"
 
 #define RESET_KIND_SHUTDOWN	0
 #define RESET_KIND_INIT		1
@@ -3030,6 +3030,19 @@ static bool tg3_phy_power_bug(struct tg3 *tp)
 	return false;
 }
 
+static bool tg3_phy_led_bug(struct tg3 *tp)
+{
+	switch (tg3_asic_rev(tp)) {
+	case ASIC_REV_5719:
+		if ((tp->phy_flags & TG3_PHYFLG_MII_SERDES) &&
+		    !tp->pci_fn)
+			return true;
+		return false;
+	}
+
+	return false;
+}
+
 static void tg3_power_down_phy(struct tg3 *tp, bool do_low_power)
 {
 	u32 val;
@@ -3077,8 +3090,9 @@ static void tg3_power_down_phy(struct tg3 *tp, bool do_low_power)
 		}
 		return;
 	} else if (do_low_power) {
-		tg3_writephy(tp, MII_TG3_EXT_CTRL,
-			     MII_TG3_EXT_CTRL_FORCE_LED_OFF);
+		if (!tg3_phy_led_bug(tp))
+			tg3_writephy(tp, MII_TG3_EXT_CTRL,
+				     MII_TG3_EXT_CTRL_FORCE_LED_OFF);
 
 		val = MII_TG3_AUXCTL_PCTL_100TX_LPWR |
 		      MII_TG3_AUXCTL_PCTL_SPR_ISOLATE |
@@ -4226,8 +4240,6 @@ static int tg3_power_down_prepare(struct tg3 *tp)
 
 static void tg3_power_down(struct tg3 *tp)
 {
-	tg3_power_down_prepare(tp);
-
 	pci_wake_from_d3(tp->pdev, tg3_flag(tp, WOL_ENABLE));
 	pci_set_power_state(tp->pdev, PCI_D3hot);
 }
@@ -6095,10 +6107,12 @@ static u64 tg3_refclk_read(struct tg3 *tp)
 /* tp->lock must be held */
 static void tg3_refclk_write(struct tg3 *tp, u64 newval)
 {
-	tw32(TG3_EAV_REF_CLCK_CTL, TG3_EAV_REF_CLCK_CTL_STOP);
+	u32 clock_ctl = tr32(TG3_EAV_REF_CLCK_CTL);
+
+	tw32(TG3_EAV_REF_CLCK_CTL, clock_ctl | TG3_EAV_REF_CLCK_CTL_STOP);
 	tw32(TG3_EAV_REF_CLCK_LSB, newval & 0xffffffff);
 	tw32(TG3_EAV_REF_CLCK_MSB, newval >> 32);
-	tw32_f(TG3_EAV_REF_CLCK_CTL, TG3_EAV_REF_CLCK_CTL_RESUME);
+	tw32_f(TG3_EAV_REF_CLCK_CTL, clock_ctl | TG3_EAV_REF_CLCK_CTL_RESUME);
 }
 
 static inline void tg3_full_lock(struct tg3 *tp, int irq_sync);
@@ -6214,6 +6228,59 @@ static int tg3_ptp_settime(struct ptp_clock_info *ptp,
 static int tg3_ptp_enable(struct ptp_clock_info *ptp,
 			  struct ptp_clock_request *rq, int on)
 {
+	struct tg3 *tp = container_of(ptp, struct tg3, ptp_info);
+	u32 clock_ctl;
+	int rval = 0;
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_PEROUT:
+		if (rq->perout.index != 0)
+			return -EINVAL;
+
+		tg3_full_lock(tp, 0);
+		clock_ctl = tr32(TG3_EAV_REF_CLCK_CTL);
+		clock_ctl &= ~TG3_EAV_CTL_TSYNC_GPIO_MASK;
+
+		if (on) {
+			u64 nsec;
+
+			nsec = rq->perout.start.sec * 1000000000ULL +
+			       rq->perout.start.nsec;
+
+			if (rq->perout.period.sec || rq->perout.period.nsec) {
+				netdev_warn(tp->dev,
+					    "Device supports only a one-shot timesync output, period must be 0\n");
+				rval = -EINVAL;
+				goto err_out;
+			}
+
+			if (nsec & (1ULL << 63)) {
+				netdev_warn(tp->dev,
+					    "Start value (nsec) is over limit. Maximum size of start is only 63 bits\n");
+				rval = -EINVAL;
+				goto err_out;
+			}
+
+			tw32(TG3_EAV_WATCHDOG0_LSB, (nsec & 0xffffffff));
+			tw32(TG3_EAV_WATCHDOG0_MSB,
+			     TG3_EAV_WATCHDOG0_EN |
+			     ((nsec >> 32) & TG3_EAV_WATCHDOG_MSB_MASK));
+
+			tw32(TG3_EAV_REF_CLCK_CTL,
+			     clock_ctl | TG3_EAV_CTL_TSYNC_WDOG0);
+		} else {
+			tw32(TG3_EAV_WATCHDOG0_MSB, 0);
+			tw32(TG3_EAV_REF_CLCK_CTL, clock_ctl);
+		}
+
+err_out:
+		tg3_full_unlock(tp);
+		return rval;
+
+	default:
+		break;
+	}
+
 	return -EOPNOTSUPP;
 }
 
@@ -6223,7 +6290,7 @@ static const struct ptp_clock_info tg3_ptp_caps = {
 	.max_adj	= 250000000,
 	.n_alarm	= 0,
 	.n_ext_ts	= 0,
-	.n_per_out	= 0,
+	.n_per_out	= 1,
 	.pps		= 0,
 	.adjfreq	= tg3_ptp_adjfreq,
 	.adjtime	= tg3_ptp_adjtime,
@@ -8538,10 +8605,10 @@ static int tg3_mem_rx_acquire(struct tg3 *tp)
 		if (!i && tg3_flag(tp, ENABLE_RSS))
 			continue;
 
-		tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev,
-						   TG3_RX_RCB_RING_BYTES(tp),
-						   &tnapi->rx_rcb_mapping,
-						   GFP_KERNEL | __GFP_ZERO);
+		tnapi->rx_rcb = dma_zalloc_coherent(&tp->pdev->dev,
+						    TG3_RX_RCB_RING_BYTES(tp),
+						    &tnapi->rx_rcb_mapping,
+						    GFP_KERNEL);
 		if (!tnapi->rx_rcb)
 			goto err_out;
 	}
@@ -8590,10 +8657,9 @@ static int tg3_alloc_consistent(struct tg3 *tp)
 {
 	int i;
 
-	tp->hw_stats = dma_alloc_coherent(&tp->pdev->dev,
-					  sizeof(struct tg3_hw_stats),
-					  &tp->stats_mapping,
-					  GFP_KERNEL | __GFP_ZERO);
+	tp->hw_stats = dma_zalloc_coherent(&tp->pdev->dev,
+					   sizeof(struct tg3_hw_stats),
+					   &tp->stats_mapping, GFP_KERNEL);
 	if (!tp->hw_stats)
 		goto err_out;
 
@@ -8601,10 +8667,10 @@ static int tg3_alloc_consistent(struct tg3 *tp)
 		struct tg3_napi *tnapi = &tp->napi[i];
 		struct tg3_hw_status *sblk;
 
-		tnapi->hw_status = dma_alloc_coherent(&tp->pdev->dev,
-						      TG3_HW_STATUS_SIZE,
-						      &tnapi->status_mapping,
-						      GFP_KERNEL | __GFP_ZERO);
+		tnapi->hw_status = dma_zalloc_coherent(&tp->pdev->dev,
+						       TG3_HW_STATUS_SIZE,
+						       &tnapi->status_mapping,
+						       GFP_KERNEL);
 		if (!tnapi->hw_status)
 			goto err_out;
 
@@ -10367,6 +10433,9 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy)
 	if (tg3_flag(tp, 5755_PLUS))
 		tp->rx_mode |= RX_MODE_IPV6_CSUM_ENABLE;
 
+	if (tg3_asic_rev(tp) == ASIC_REV_5762)
+		tp->rx_mode |= RX_MODE_IPV4_FRAG_FIX;
+
 	if (tg3_flag(tp, ENABLE_RSS))
 		tp->rx_mode |= RX_MODE_RSS_ENABLE |
 			       RX_MODE_RSS_ITBL_HASH_BITS_7 |
@@ -11502,7 +11571,7 @@ static int tg3_close(struct net_device *dev)
 	memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev));
 	memset(&tp->estats_prev, 0, sizeof(tp->estats_prev));
 
-	tg3_power_down(tp);
+	tg3_power_down_prepare(tp);
 
 	tg3_carrier_off(tp);
 
@@ -11724,9 +11793,6 @@ static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	if (tg3_flag(tp, NO_NVRAM))
 		return -EINVAL;
 
-	if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
-		return -EAGAIN;
-
 	offset = eeprom->offset;
 	len = eeprom->len;
 	eeprom->len = 0;
@@ -11784,9 +11850,6 @@ static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	u8 *buf;
 	__be32 start, end;
 
-	if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
-		return -EAGAIN;
-
 	if (tg3_flag(tp, NO_NVRAM) ||
 	    eeprom->magic != TG3_EEPROM_MAGIC)
 		return -EINVAL;
@@ -13515,7 +13578,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 			tg3_phy_start(tp);
 	}
 	if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
-		tg3_power_down(tp);
+		tg3_power_down_prepare(tp);
 
 }
 
@@ -15917,7 +15980,7 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent)
 	 */
 	if (tg3_flag(tp, 5780_CLASS)) {
 		tg3_flag_set(tp, 40BIT_DMA_BUG);
-		tp->msi_cap = pci_find_capability(tp->pdev, PCI_CAP_ID_MSI);
+		tp->msi_cap = tp->pdev->msi_cap;
 	} else {
 		struct pci_dev *bridge = NULL;
 
@@ -17547,11 +17610,6 @@ static int tg3_init_one(struct pci_dev *pdev,
 	    tg3_asic_rev(tp) == ASIC_REV_5762)
 		tg3_flag_set(tp, PTP_CAPABLE);
 
-	if (tg3_flag(tp, 5717_PLUS)) {
-		/* Resume a low-power mode */
-		tg3_frob_aux_power(tp, false);
-	}
-
 	tg3_timer_init(tp);
 
 	tg3_carrier_off(tp);
@@ -17755,6 +17813,23 @@ out:
 
 static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
 
+static void tg3_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct tg3 *tp = netdev_priv(dev);
+
+	rtnl_lock();
+	netif_device_detach(dev);
+
+	if (netif_running(dev))
+		dev_close(dev);
+
+	if (system_state == SYSTEM_POWER_OFF)
+		tg3_power_down(tp);
+
+	rtnl_unlock();
+}
+
 /**
  * tg3_io_error_detected - called when PCI error is detected
  * @pdev: Pointer to PCI device
@@ -17914,6 +17989,7 @@ static struct pci_driver tg3_driver = {
 	.remove		= tg3_remove_one,
 	.err_handler	= &tg3_err_handler,
 	.driver.pm	= &tg3_pm_ops,
+	.shutdown	= tg3_shutdown,
 };
 
 module_pci_driver(tg3_driver);

drivers/net/ethernet/broadcom/tg3.h

@@ -532,6 +532,7 @@
 #define  RX_MODE_RSS_ITBL_HASH_BITS_7	 0x00700000
 #define  RX_MODE_RSS_ENABLE		 0x00800000
 #define  RX_MODE_IPV6_CSUM_ENABLE	 0x01000000
+#define  RX_MODE_IPV4_FRAG_FIX		 0x02000000
 #define MAC_RX_STATUS			0x0000046c
 #define  RX_STATUS_REMOTE_TX_XOFFED	 0x00000001
 #define  RX_STATUS_XOFF_RCVD		 0x00000002
@@ -1818,12 +1819,21 @@
 #define TG3_EAV_REF_CLCK_CTL		0x00006908
 #define  TG3_EAV_REF_CLCK_CTL_STOP	 0x00000002
 #define  TG3_EAV_REF_CLCK_CTL_RESUME	 0x00000004
+#define  TG3_EAV_CTL_TSYNC_GPIO_MASK	 (0x3 << 16)
+#define  TG3_EAV_CTL_TSYNC_WDOG0	 (1 << 17)
+
+#define TG3_EAV_WATCHDOG0_LSB		0x00006918
+#define TG3_EAV_WATCHDOG0_MSB		0x0000691c
+#define  TG3_EAV_WATCHDOG0_EN		 (1 << 31)
+#define  TG3_EAV_WATCHDOG_MSB_MASK	0x7fffffff
+
 #define TG3_EAV_REF_CLK_CORRECT_CTL	0x00006928
 #define  TG3_EAV_REF_CLK_CORRECT_EN	 (1 << 31)
 #define  TG3_EAV_REF_CLK_CORRECT_NEG	 (1 << 30)
 
 #define TG3_EAV_REF_CLK_CORRECT_MASK	0xffffff
-/* 0x690c --> 0x7000 unused */
+
+/* 0x692c --> 0x7000 unused */
 
 /* NVRAM Control registers */
 #define NVRAM_CMD			0x00007000

drivers/net/ethernet/brocade/bna/bna_tx_rx.c

@@ -1419,7 +1419,7 @@ static void bna_rx_sm_start_wait_entry(struct bna_rx *rx)
 	bna_bfi_rx_enet_start(rx);
 }
 
-void
+static void
 bna_rx_sm_stop_wait_entry(struct bna_rx *rx)
 {
 }
@@ -1472,7 +1472,7 @@ static void bna_rx_sm_rxf_start_wait_entry(struct bna_rx *rx)
 	bna_rxf_start(&rx->rxf);
 }
 
-void
+static void
 bna_rx_sm_rxf_stop_wait_entry(struct bna_rx *rx)
 {
 }
@@ -1528,7 +1528,7 @@ bna_rx_sm_start_stop_wait(struct bna_rx *rx, enum bna_rx_event event)
 	}
 }
 
-void
+static void
 bna_rx_sm_started_entry(struct bna_rx *rx)
 {
 	struct bna_rxp *rxp;
@@ -1593,12 +1593,12 @@ static void bna_rx_sm_rxf_start_wait(struct bna_rx *rx,
 	}
 }
 
-void
+static void
 bna_rx_sm_cleanup_wait_entry(struct bna_rx *rx)
 {
 }
 
-void
+static void
 bna_rx_sm_cleanup_wait(struct bna_rx *rx, enum bna_rx_event event)
 {
 	switch (event) {

drivers/net/ethernet/brocade/bna/cna.h

@@ -37,8 +37,8 @@
 
 extern char bfa_version[];
 
-#define CNA_FW_FILE_CT	"ctfw-3.2.1.0.bin"
-#define CNA_FW_FILE_CT2	"ct2fw-3.2.1.0.bin"
+#define CNA_FW_FILE_CT	"ctfw-3.2.1.1.bin"
+#define CNA_FW_FILE_CT2	"ct2fw-3.2.1.1.bin"
 #define FC_SYMNAME_MAX	256	/*!< max name server symbolic name size */
 
 #pragma pack(1)

drivers/net/ethernet/cadence/at91_ether.c

@@ -304,7 +304,7 @@ MODULE_DEVICE_TABLE(of, at91ether_dt_ids);
 /* Detect MAC & PHY and perform ethernet interface initialization */
 static int __init at91ether_probe(struct platform_device *pdev)
 {
-	struct macb_platform_data *board_data = pdev->dev.platform_data;
+	struct macb_platform_data *board_data = dev_get_platdata(&pdev->dev);
 	struct resource *regs;
 	struct net_device *dev;
 	struct phy_device *phydev;